Saving train state of step 90000

.gitignore

@@ -0,0 +1 @@
+wandb

accelerate_config.yaml

@@ -0,0 +1,17 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+distributed_type: MULTI_GPU
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+gpu_ids: all
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

checkpoint-80000-epoch-5/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d85a6ebcfaea697deb81a9f43cf52b763722cc63c52559be99475194f3b1740
+size 3652769047

checkpoint-80000-epoch-5/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ed77445bae74c0a44de014644335672082db652c167e03307f5aa69f497029
+size 2588465818

checkpoint-80000-epoch-5/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bee040cadf66c07cc28951d8b63f5309317c467c935239899967dedde236356
+size 16100

checkpoint-80000-epoch-5/random_states_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2984f6c11e0d6baba6e153c36e02cf7d8849f435a8e1d10db3db9422a5e14f
+size 16100

checkpoint-80000-epoch-5/random_states_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0328ba0db514b5427f0cf5728abf82349345bec8a02097c30900ec57f433da11
+size 16100

checkpoint-80000-epoch-5/random_states_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668cc4578435da562a838c3860a81ef62a34fdfed1920ccebb7657eb586c14cb
+size 16100

checkpoint-80000-epoch-5/random_states_4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c856097a2b0832cc85eba37f9cd1be76e0d395fe4b2c99ef3153199386dae5e5
+size 16100

checkpoint-80000-epoch-5/random_states_5.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d11b3bb1f3959f58be8c638fb21de1e89e54c13aa716a178687cb1fc51ac99
+size 16100

checkpoint-80000-epoch-5/random_states_6.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18447190b31cbfd6ac8565a46dfbdc82123f510bef0eb0a72313d1150001b8f4
+size 16100

checkpoint-80000-epoch-5/random_states_7.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025b2bf49a9a6fe2a6fd8cb7a98ba98f4eb439e04b5aa68fd3285c8c109bdc4f
+size 16100

checkpoint-80000-epoch-5/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd55300ad4b9da07287969193b88215d1af9b5d03f7bf3a833f1b260aa6434c4
+size 1000

checkpoint-90000-epoch-6/config.json

@@ -0,0 +1,278 @@
+{
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "parler-tts/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "./parler-tts-untrained-600M/decoder",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_embeddings": true,
+    "rope_theta": 10000.0,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "prompt_cross_attention": true,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "vocab_size": 32128
+}

checkpoint-90000-epoch-6/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1,
+  "key": 10,
+  "max_length": 2580,
+  "pad_token_id": 1024,
+  "transformers_version": "4.40.2"
+}

checkpoint-90000-epoch-6/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a5f279e2029513a27b4cded580e595a78c5fc272f40cb7f588433d7958d46c
+size 3652769047

checkpoint-90000-epoch-6/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8328177320aeb4953e3eec0bf9d69faaa0252580a421c044139beb4a6331ca7
+size 2588465818

checkpoint-90000-epoch-6/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce59f0c776bd98a152d59388c7b005bc4a240f161451d365033b376ffdbdf689
+size 16100

checkpoint-90000-epoch-6/random_states_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9023097fa78daf107b4ab8d45d5c2428ce1dfcfa78f1325792412a2fc1422961
+size 16100

checkpoint-90000-epoch-6/random_states_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae413302aa9d35ab8fda74453e73117f5f7bb061667d47682aceeec97a48d1b
+size 16100

checkpoint-90000-epoch-6/random_states_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22951f7c252eb5c607a491f9a4aece64566703c5a3454daa80b5a9335031005d
+size 16100

checkpoint-90000-epoch-6/random_states_4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63052cdf7dd342cee03f75c8a78acd9ee45ca352bbfafa6fe46779ca27905489
+size 16164

checkpoint-90000-epoch-6/random_states_5.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4610b40691a1373dff81de30c9bc043ce4f6a4f82d18d910d9202ba688cba95
+size 16100

checkpoint-90000-epoch-6/random_states_6.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a333a3646432bc3d5f3cb8d6ccf35d3121cf07c5b6f5652c6c3b7e6086f748
+size 16100

checkpoint-90000-epoch-6/random_states_7.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72846ff2a7e97a862a1b449d5b5647f99109b910e1c68bc4a6410f2afeb6b5b3
+size 16100

checkpoint-90000-epoch-6/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6c681cda1d31cf3664adcef373dcad0d17378550a5e96a62ea22bcce6a8e0d
+size 1000

config.json

@@ -0,0 +1,278 @@
+{
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "parler-tts/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "./parler-tts-untrained-600M/decoder",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_embeddings": true,
+    "rope_theta": 10000.0,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "prompt_cross_attention": true,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "vocab_size": 32128
+}

parler_tts/__init__.py

@@ -0,0 +1,16 @@
+__version__ = "0.1"
+
+
+from .configuration_parler_tts import ParlerTTSConfig, ParlerTTSDecoderConfig
+from .modeling_parler_tts import (
+    ParlerTTSForCausalLM,
+    ParlerTTSForConditionalGeneration,
+    apply_delay_pattern_mask,
+    build_delay_pattern_mask,
+)
+
+from .dac_wrapper import DACConfig, DACModel
+from transformers import AutoConfig, AutoModel
+
+AutoConfig.register("dac", DACConfig)
+AutoModel.register(DACConfig, DACModel)

parler_tts/configuration_parler_tts.py

@@ -0,0 +1,249 @@
+# coding=utf-8
+# Copyright 2024 and The HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" Parler-TTS model configuration"""
+
+from transformers import AutoConfig, logging
+from transformers.configuration_utils import PretrainedConfig
+
+
+logger = logging.get_logger(__name__)
+
+MUSICGEN_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "facebook/parler_tts-small": "https://huggingface.co/facebook/parler_tts-small/resolve/main/config.json",
+    # See all ParlerTTS models at https://huggingface.co/models?filter=parler_tts
+}
+
+
+class ParlerTTSDecoderConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of an [`ParlerTTSDecoder`]. It is used to instantiate a
+    Parler-TTS decoder according to the specified arguments, defining the model architecture. Instantiating a
+    configuration with the defaults will yield a similar configuration to that of the Parler-TTS
+    [facebook/parler_tts-small](https://huggingface.co/facebook/parler_tts-small) architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 2049):
+            Vocabulary size of the ParlerTTSDecoder model. Defines the number of different tokens that can be
+            represented by the `inputs_ids` passed when calling [`ParlerTTSDecoder`].
+        hidden_size (`int`, *optional*, defaults to 1024):
+            Dimensionality of the layers and the pooler layer.
+        num_hidden_layers (`int`, *optional*, defaults to 24):
+            Number of decoder layers.
+        num_attention_heads (`int`, *optional*, defaults to 16):
+            Number of attention heads for each attention layer in the Transformer block.
+        ffn_dim (`int`, *optional*, defaults to 4096):
+            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer block.
+        activation_function (`str` or `function`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the decoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"silu"` and `"gelu_new"` are supported.
+        dropout (`float`, *optional*, defaults to 0.1):
+            The dropout probability for all fully connected layers in the embeddings, text_encoder, and pooler.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        activation_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for activations inside the fully connected layer.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with. Typically, set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        initializer_factor (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        layerdrop (`float`, *optional*, defaults to 0.0):
+            The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
+            for more details.
+        scale_embedding (`bool`, *optional*, defaults to `False`):
+            Scale embeddings by diving by sqrt(hidden_size).
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether the model should return the last key/values attentions (not used by all models)
+        num_codebooks (`int`, *optional*, defaults to 4):
+            The number of parallel codebooks forwarded to the model.
+        tie_word_embeddings(`bool`, *optional*, defaults to `False`):
+            Whether input and output word embeddings should be tied.
+        rope_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to use ROPE or absolute positional embeddings.
+        rope_theta (`float`, *optional*, defaults to 100000.0):
+            The base period of the RoPE embeddings.
+    """
+
+    model_type = "parler_tts_decoder"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=2049,  # vocab size = 2048 (encodec vocab size) + 1 (eos)
+        max_position_embeddings=2048,
+        num_hidden_layers=24,
+        ffn_dim=4096,
+        num_attention_heads=16,
+        layerdrop=0.0,
+        use_cache=True,
+        activation_function="gelu",
+        hidden_size=1024,
+        dropout=0.1,
+        attention_dropout=0.0,
+        activation_dropout=0.0,
+        initializer_factor=0.02,
+        scale_embedding=False,
+        num_codebooks=4,
+        pad_token_id=2048,
+        bos_token_id=2049,
+        eos_token_id=2048,
+        tie_word_embeddings=False,
+        rope_embeddings=False,
+        rope_theta=10_000.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.ffn_dim = ffn_dim
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.dropout = dropout
+        self.attention_dropout = attention_dropout
+        self.activation_dropout = activation_dropout
+        self.activation_function = activation_function
+        self.initializer_factor = initializer_factor
+        self.layerdrop = layerdrop
+        self.use_cache = use_cache
+        self.scale_embedding = scale_embedding  # scale factor will be sqrt(d_model) if True
+        self.num_codebooks = num_codebooks
+        self.rope_embeddings = rope_embeddings
+        self.rope_theta = rope_theta
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+
+class ParlerTTSConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`ParlerTTSModel`]. It is used to instantiate a
+    Parler-TTS model according to the specified arguments, defining the text encoder, audio encoder and Parler-TTS decoder
+    configs.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 1024):
+            Vocabulary size of the prompt token ids. Defines the number of different tokens that can be
+            represented by the `prompt_inputs_ids`.
+        prompt_cross_attention (`bool`, *optional*, defaults to `False`):
+            Whether to use cross-attention conditioning for the prompt (as well as the description).
+        kwargs (*optional*):
+            Dictionary of keyword arguments. Notably:
+
+                - **text_encoder** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that
+                  defines the text encoder config.
+                - **audio_encoder** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that
+                  defines the audio encoder config.
+                - **decoder** ([`PretrainedConfig`], *optional*) -- An instance of a configuration object that defines
+                  the decoder config.
+
+    Example:
+
+    ```python
+    >>> from transformers import (
+    ...     ParlerTTSConfig,
+    ...     ParlerTTSDecoderConfig,
+    ...     T5Config,
+    ...     EncodecConfig,
+    ...     ParlerTTSForConditionalGeneration,
+    ... )
+
+    >>> # Initializing text encoder, audio encoder, and decoder model configurations
+    >>> text_encoder_config = T5Config()
+    >>> audio_encoder_config = EncodecConfig()
+    >>> decoder_config = ParlerTTSDecoderConfig()
+
+    >>> configuration = ParlerTTSConfig.from_sub_models_config(
+    ...     text_encoder_config, audio_encoder_config, decoder_config
+    ... )
+
+    >>> # Initializing a ParlerTTSForConditionalGeneration (with random weights) from the facebook/parler_tts-small style configuration
+    >>> model = ParlerTTSForConditionalGeneration(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    >>> config_text_encoder = model.config.text_encoder
+    >>> config_audio_encoder = model.config.audio_encoder
+    >>> config_decoder = model.config.decoder
+
+    >>> # Saving the model, including its configuration
+    >>> model.save_pretrained("parler_tts-model")
+
+    >>> # loading model and config from pretrained folder
+    >>> parler_tts_config = ParlerTTSConfig.from_pretrained("parler_tts-model")
+    >>> model = ParlerTTSForConditionalGeneration.from_pretrained("parler_tts-model", config=parler_tts_config)
+    ```"""
+
+    model_type = "parler_tts"
+    is_composition = True
+
+    def __init__(self, vocab_size=1024, prompt_cross_attention=False, **kwargs):
+        super().__init__(**kwargs)
+        if "text_encoder" not in kwargs or "audio_encoder" not in kwargs or "decoder" not in kwargs:
+            raise ValueError("Config has to be initialized with text_encoder, audio_encoder and decoder config")
+
+        text_encoder_config = kwargs.pop("text_encoder")
+        text_encoder_model_type = text_encoder_config.pop("model_type")
+
+        audio_encoder_config = kwargs.pop("audio_encoder")
+        audio_encoder_model_type = audio_encoder_config.pop("model_type")
+
+        decoder_config = kwargs.pop("decoder")
+
+        self.vocab_size = vocab_size
+        self.prompt_cross_attention = prompt_cross_attention
+        self.text_encoder = AutoConfig.for_model(text_encoder_model_type, **text_encoder_config)
+        self.audio_encoder = AutoConfig.for_model(audio_encoder_model_type, **audio_encoder_config)
+        self.decoder = ParlerTTSDecoderConfig(**decoder_config)
+        self.is_encoder_decoder = True
+
+    @classmethod
+    def from_sub_models_config(
+        cls,
+        text_encoder_config: PretrainedConfig,
+        audio_encoder_config: PretrainedConfig,
+        decoder_config: ParlerTTSDecoderConfig,
+        **kwargs,
+    ):
+        r"""
+        Instantiate a [`ParlerTTSConfig`] (or a derived class) from text encoder, audio encoder and decoder
+        configurations.
+
+        Returns:
+            [`ParlerTTSConfig`]: An instance of a configuration object
+        """
+
+        return cls(
+            text_encoder=text_encoder_config.to_dict(),
+            audio_encoder=audio_encoder_config.to_dict(),
+            decoder=decoder_config.to_dict(),
+            **kwargs,
+        )
+
+    @property
+    # This is a property because you might want to change the codec model on the fly
+    def sampling_rate(self):
+        return self.audio_encoder.sampling_rate

parler_tts/dac_wrapper/__init__.py

@@ -0,0 +1,2 @@
+from .configuration_dac import DACConfig
+from .modeling_dac import DACModel

parler_tts/dac_wrapper/configuration_dac.py

@@ -0,0 +1,25 @@
+from transformers import PretrainedConfig
+from typing import List
+
+
+class DACConfig(PretrainedConfig):
+    model_type = "dac"
+
+    def __init__(
+        self,
+        num_codebooks: int = 9,
+        model_bitrate: int = 8,  # kbps
+        codebook_size: int = 1024,
+        latent_dim: int = 1024,
+        frame_rate: int = 86,
+        sampling_rate: int = 44100,
+        **kwargs,
+    ):
+        self.codebook_size = codebook_size
+        self.model_bitrate = model_bitrate
+        self.latent_dim = latent_dim
+        self.num_codebooks = num_codebooks
+        self.frame_rate = frame_rate
+        self.sampling_rate = sampling_rate
+
+        super().__init__(**kwargs)

parler_tts/dac_wrapper/modeling_dac.py

@@ -0,0 +1,137 @@
+import torch
+
+from transformers import PreTrainedModel
+from transformers.models.encodec.modeling_encodec import EncodecEncoderOutput, EncodecDecoderOutput
+from .configuration_dac import DACConfig
+
+from dac.model import DAC
+
+
+# model doesn't support batching yet
+
+
+class DACModel(PreTrainedModel):
+    config_class = DACConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+
+        self.model = DAC(
+            n_codebooks=config.num_codebooks,
+            latent_dim=config.latent_dim,
+            codebook_size=config.codebook_size,
+        )
+
+    def encode(
+        self, input_values, padding_mask=None, bandwidth=None, return_dict=None, n_quantizers=None, sample_rate=None
+    ):
+        """
+        Encodes the input audio waveform into discrete codes.
+
+        Args:
+            input_values (`torch.Tensor` of shape `(batch_size, channels, sequence_length)`):
+                Float values of the input audio waveform.
+            padding_mask (`torch.Tensor` of shape `(batch_size, channels, sequence_length)`):
+                Padding mask used to pad the `input_values`.
+            bandwidth (`float`, *optional*):
+                Not used, kept to have the same inferface as HF encodec.
+            n_quantizers (`int`, *optional*) :
+                Number of quantizers to use, by default None
+                If None, all quantizers are used.
+            sample_rate (`int`, *optional*) :
+                Signal sampling_rate
+
+        Returns:
+            A list of frames containing the discrete encoded codes for the input audio waveform, along with rescaling
+            factors for each chunk when `normalize` is True. Each frames is a tuple `(codebook, scale)`, with
+            `codebook` of shape `[batch_size, num_codebooks, frames]`.
+            Scale is not used here.
+
+        """
+        _, channels, input_length = input_values.shape
+
+        if channels < 1 or channels > 2:
+            raise ValueError(f"Number of audio channels must be 1 or 2, but got {channels}")
+
+        audio_data = self.model.preprocess(input_values, sample_rate)
+
+        return_dict = return_dict if return_dict is not None else self.config.return_dict
+
+        # TODO: for now, no chunk length
+
+        chunk_length = None  # self.config.chunk_length
+        if chunk_length is None:
+            chunk_length = input_length
+            stride = input_length
+        else:
+            stride = self.config.chunk_stride
+
+        if padding_mask is None:
+            padding_mask = torch.ones_like(input_values).bool()
+
+        encoded_frames = []
+        scales = []
+
+        step = chunk_length - stride
+        if (input_length % stride) - step != 0:
+            raise ValueError(
+                "The input length is not properly padded for batched chunked decoding. Make sure to pad the input correctly."
+            )
+
+        for offset in range(0, input_length - step, stride):
+            mask = padding_mask[..., offset : offset + chunk_length].bool()
+            frame = audio_data[:, :, offset : offset + chunk_length]
+
+            scale = None
+
+            _, encoded_frame, _, _, _ = self.model.encode(frame, n_quantizers=n_quantizers)
+            encoded_frames.append(encoded_frame)
+            scales.append(scale)
+
+        encoded_frames = torch.stack(encoded_frames)
+
+        if not return_dict:
+            return (encoded_frames, scales)
+
+        return EncodecEncoderOutput(encoded_frames, scales)
+
+    def decode(
+        self,
+        audio_codes,
+        audio_scales,
+        padding_mask=None,
+        return_dict=None,
+    ):
+        """
+        Decodes the given frames into an output audio waveform.
+
+        Note that the output might be a bit bigger than the input. In that case, any extra steps at the end can be
+        trimmed.
+
+        Args:
+            audio_codes (`torch.FloatTensor`  of shape `(batch_size, nb_chunks, chunk_length)`, *optional*):
+                Discret code embeddings computed using `model.encode`.
+            audio_scales (`torch.Tensor` of shape `(batch_size, nb_chunks)`, *optional*):
+                Not used, kept to have the same inferface as HF encodec.
+            padding_mask (`torch.Tensor` of shape `(batch_size, channels, sequence_length)`):
+                Padding mask used to pad the `input_values`.
+                Not used yet, kept to have the same inferface as HF encodec.
+            return_dict (`bool`, *optional*):
+                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
+
+        """
+        return_dict = return_dict or self.config.return_dict
+
+        # TODO: for now, no chunk length
+
+        if len(audio_codes) != 1:
+            raise ValueError(f"Expected one frame, got {len(audio_codes)}")
+
+        audio_values = self.model.quantizer.from_codes(audio_codes.squeeze(0))[0]
+        audio_values = self.model.decode(audio_values)
+        if not return_dict:
+            return (audio_values,)
+        return EncodecDecoderOutput(audio_values)
+
+    def forward(self, tensor):
+        raise ValueError(f"`DACModel.forward` not implemented yet")

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "chunk_length_s": null,
+  "feature_extractor_type": "EncodecFeatureExtractor",
+  "feature_size": 1,
+  "overlap": null,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 44100
+}

slurm_job.slurm

@@ -0,0 +1,74 @@
+#!/bin/bash
+#SBATCH --job-name=parler-tts
+#SBATCH --nodes=1
+# set 48h for job wall time limit
+#SBATCH --time=48:00:00
+#SBATCH --ntasks-per-node=1          # crucial - only 1 task per dist per node!
+#SBATCH --cpus-per-task=32
+#SBATCH --gres=gpu:8
+#SBATCH --partition=hopper-prod
+#SBATCH --output=/fsx/sanchit/logs/%x-%j.out
+
+set -x -e
+
+# START EDIT
+source ~/.bashrc
+source /fsx/sanchit/miniconda3/bin/activate venv
+
+LOG_PATH="/fsx/sanchit/logs/main_log.txt"
+SAVE_DIR="/fsx/sanchit"
+# END EDIT
+
+echo "START TIME: $(date)"
+
+GPUS_PER_NODE=8
+NNODES=$SLURM_NNODES
+
+# so processes know who to talk to
+MASTER_ADDR=`scontrol show hostnames $SLURM_JOB_NODELIST | head -n 1`
+
+# From https://i.hsfzxjy.site/2021-03-10-obtain-a-random-unused-tcp-port-with-bash/
+function unused_port() {
+    N=${1:-1}
+    comm -23 \
+        <(seq "1025" "65535" | sort) \
+        <(ss -Htan |
+            awk '{print $4}' |
+            cut -d':' -f2 |
+            sort -u) |
+        shuf |
+        head -n "$N"
+}
+MASTER_PORT=$(unused_port)
+
+# export TORCH_CPP_LOG_LEVEL=INFO
+# export TORCH_DISTRIBUTED_DEBUG=DETAIL
+
+export LAUNCHER="python -u -m accelerate.commands.launch --config_file ./accelerate_config.yaml"
+
+export PROGRAM="./training/run_parler_tts_training.py ./starting_point_0.01_rope.json"
+export CMD="$LAUNCHER $PROGRAM"
+echo $CMD
+
+SRUN_ARGS=" \
+    --wait=60 \
+    --kill-on-bad-exit=1 \
+    "
+
+# py-spy top -s -i -n -- $LAUNCHER --node_rank $SLURM_PROCID --role $SLURMD_NODENAME: $CMD
+clear; srun $SRUN_ARGS --jobid $SLURM_JOB_ID bash -c "$CMD" 2>&1 | tee -a $SAVE_DIR/logs/main_log.txt
+
+
+# srun error handling:
+# --wait=60: wait 60 sec after the first task terminates before terminating all remaining tasks
+# --kill-on-bad-exit=1: terminate a step if any task exits with a non-zero exit code
+
+# SRUN_ARGS=" \
+#     --wait=60 \
+#     --kill-on-bad-exit=1 \
+#     "
+#
+# # py-spy top -s -i -n -- $LAUNCHER --node_rank $SLURM_PROCID --role $SLURMD_NODENAME: $CMD
+# clear; srun $SRUN_ARGS --jobid $SLURM_JOBID bash -c "$CMD" 2>&1 | tee -a $SAVE_DIR/logs/main_log.txt
+
+echo "END TIME: $(date)"

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

starting_point_0.01_rope.json

@@ -0,0 +1,79 @@
+{
+    "model_name_or_path": "parler-tts/parler-tts-untrained-600M-cross-attention-rope",
+    "save_to_disk":  "/fsx/sanchit/10k_hours_processed_punctuated",
+    "temporary_save_to_disk": "/scratch/tmp_dataset_audio/",
+    "push_to_hub": true,
+
+
+    "feature_extractor_name":"ylacombe/dac_44khZ_8kbps",
+    "description_tokenizer_name":"google/flan-t5-base",
+    "prompt_tokenizer_name":"google/flan-t5-base",
+
+    "report_to": ["wandb"],
+    "wandb_run_name": "parler-tts-600M-cross-attention-rope-decayed",
+    "overwrite_output_dir": false,
+    "save_total_limit": 2,
+    "output_dir": "./",
+
+    "train_dataset_name": "blabble-io/libritts_r+blabble-io/libritts_r+blabble-io/libritts_r+parler-tts/mls_eng_10k",
+    "train_metadata_dataset_name": "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated",
+    "train_dataset_config_name": "clean+clean+other+default",
+    "train_split_name": "train.clean.360+train.clean.100+train.other.500+train",
+
+    "eval_dataset_name": "blabble-io/libritts_r+parler-tts/mls_eng_10k",
+    "eval_metadata_dataset_name": "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated",
+    "eval_dataset_config_name": "other+default",
+    "eval_split_name": "test.other+test",
+
+    "target_audio_column_name": "audio", 
+    "description_column_name": "text_description",
+    "prompt_column_name": "text",
+
+    "max_eval_samples": 96,
+    
+    "max_duration_in_seconds": 30,
+    "min_duration_in_seconds": 2.0,
+    "max_text_length": 400,
+
+    "group_by_length": true,
+
+    "add_audio_samples_to_wandb": true,
+    "id_column_name": "id",
+
+    "preprocessing_num_workers": 8,
+
+    "do_train": true,
+    "num_train_epochs": 15,
+    "gradient_accumulation_steps": 8,
+    "gradient_checkpointing": false,
+    "per_device_train_batch_size": 3,
+    "learning_rate": 0.00095,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.99,
+    "weight_decay": 0.01,
+
+    "lr_scheduler_type": "cosine",
+    "warmup_steps":  20000,
+
+
+    "logging_steps": 1000,
+    "freeze_text_encoder": true,
+
+
+    "do_eval": true, 
+    "predict_with_generate": true,
+    "include_inputs_for_metrics": true,
+    "evaluation_strategy": "steps",
+    "eval_steps": 10000,
+    "save_steps": 10000,
+
+    "per_device_eval_batch_size": 12,
+
+    "audio_encoder_per_device_batch_size":20,
+    "dtype": "bfloat16",
+    "seed": 456,
+    "ddp_timeout": 7200,
+
+    "dataloader_num_workers":8
+}
+

tokenizer_config.json

@@ -0,0 +1,938 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training/README.md

@@ -0,0 +1,211 @@
+# Training Parler-TTS
+
+<a target="_blank" href="https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_on_a_single_speaker_dataset.ipynb"> 
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> 
+</a>
+
+**TL;DR:** After having followed the [installation steps](#requirements), you can reproduce the [Parler-TTS Mini v0.1](https://huggingface.co/parler-tts/parler_tts_mini_v0.1) training recipe with the following command line:
+
+```sh
+accelerate launch ./training/run_parler_tts_training.py ./helpers/training_configs/starting_point_0.01.json
+```
+
+-------------
+
+This sub-folder contains all the information to train or fine-tune your own Parler-TTS model. It consists of:
+- [1. An introduction to the Parler-TTS architecture](#a-architecture)
+- [2. First steps to get started](#b-getting-started)
+- [3. Training guide](#c-training)
+
+> [!IMPORTANT]
+> You can also follow [this fine-tuning guide](https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_on_a_single_speaker_dataset.ipynb) on a mono-speaker dataset example.
+
+## 1. Architecture
+
+At the moment, Parler-TTS architecture is a carbon copy of the [MusicGen architecture](https://huggingface.co/docs/transformers/v4.39.3/en/model_doc/musicgen#model-structure) and can be decomposed into three distinct stages:
+1. Text encoder: maps the text descriptions to a sequence of hidden-state representations. Parler-TTS uses a frozen text encoder initialised entirely from Flan-T5
+2. Parler-TTS decoder: a language model (LM) that auto-regressively generates audio tokens (or codes) conditional on the encoder hidden-state representations
+3. Audio codec: used to recover the audio waveform from the audio tokens predicted by the decoder. We use the [DAC model](https://github.com/descriptinc/descript-audio-codec) from Descript, although other codec models, such as [EnCodec](https://huggingface.co/facebook/encodec_48khz), can also be used
+
+Parler-TTS however introduces some small tweaks:
+- The text **description** is passed through the text encoder and used in the cross-attention layers of the decoder.
+- The text **prompt** is simply passed through an embedding layer and concatenated to the decoder input hidden states.
+- The audio encoder used is [**DAC**](https://descript.notion.site/Descript-Audio-Codec-11389fce0ce2419891d6591a68f814d5) instead of [Encodec](https://github.com/facebookresearch/encodec), as it exhibits better quality.
+
+
+## 2. Getting started
+
+To get started, you need to follow a few steps:
+1. Install the requirements.
+2. Find or initialize the model you'll train on. 
+3. Find and/or annotate the dataset you'll train your model on.
+
+### Requirements
+
+The Parler-TTS code is written in [PyTorch](https://pytorch.org) and [Accelerate](https://huggingface.co/docs/accelerate/index). It uses some additional requirements, like [wandb](https://wandb.ai/), especially for logging and evaluation.
+
+To install the package for training, you need to clone the repository from source...
+
+```bash
+git clone https://github.com/huggingface/parler-tts.git
+cd parler-tts
+```
+
+... And then install the requirements:
+
+```bash
+pip install -e .[train]
+```
+
+Optionally, you can create a wandb account and login to it by following [this guide](https://docs.wandb.ai/quickstart). [`wandb`](https://docs.wandb.ai/) allows for better tracking of the experiments metrics and losses.
+
+You also have the option to configure Accelerate by running the following command. Note that you should set the number of GPUs you wish to use for training, and also the data type (dtype) to your preferred dtype for training/inference (e.g. `bfloat16` on A100 GPUs, `float16` on V100 GPUs, etc.):
+
+```bash
+accelerate config
+```
+
+Lastly, you can link you Hugging Face account so that you can push model repositories on the Hub. This will allow you to save your trained models on the Hub so that you can share them with the community. Run the command:
+
+```bash
+git config --global credential.helper store
+huggingface-cli login
+```
+And then enter an authentication token from https://huggingface.co/settings/tokens. Create a new token if you do not have one already. You should make sure that this token has "write" privileges.
+
+### Initialize a model from scratch or use a pre-trained one.
+
+Depending on your compute resources and your dataset, you need to choose between fine-tuning a pre-trained model and training a new model from scratch.
+
+In that sense, we released a 600M checkpoint trained on 10.5K hours of annotated data under the repository id: [`parler-tts/parler_tts_mini_v0.1`](https://huggingface.co/parler-tts/parler_tts_mini_v0.1), that you can fine-tune for your own use-case.
+
+You can also train you own model from scratch. You can find [here](/helpers/model_init_scripts/) examples on how to initialize a model from scratch. For example, you can initialize a dummy model with:
+
+```sh
+python helpers/model_init_scripts/init_dummy_model.py ./parler-tts-untrained-dummy --text_model "google-t5/t5-small" --audio_model "parler-tts/dac_44khZ_8kbps"
+```
+
+In the rest of this guide, and to reproduce the Parler-TTS Mini v0.1 training recipe, we'll use a 600M parameters model that we'll initialize with:
+
+```sh
+python helpers/model_init_scripts/init_model_600M.py ./parler-tts-untrained-600M --text_model "google/flan-t5-base" --audio_model "parler-tts/dac_44khZ_8kbps"
+```
+
+
+### Create or find datasets
+
+To train your own Parler-TTS, you need datasets with 3 main features:
+- speech data
+- text transcription of the speech data
+- conditionning text description - that you can create using [Data-Speech](https://github.com/huggingface/dataspeech), a library that allows you to annotate the speaker and utterance characteristics with natural language description.
+
+Note that we made the choice to use description of the main speech characteristics (speaker pitch, speaking rate, level of noise, etc.) but that you are free to use any handmade or generated text description that makes sense.
+
+To train Parler-TTS Mini v0.1, we used:
+* The full [LibriTTS-R dataset](https://huggingface.co/datasets/blabble-io/libritts_r), a 1K hours high-quality speech dataset.
+* A [10K hours subset](https://huggingface.co/datasets/parler-tts/mls_eng_10k) of [Multilingual LibriSpeech](https://huggingface.co/datasets/facebook/multilingual_librispeech).
+
+Both datasets have been annotated using the [Data-Speech](https://github.com/huggingface/dataspeech) recipe, respectively [here](https://huggingface.co/datasets/parler-tts/libritts_r_tags_tagged_10k_generated) and [here](https://huggingface.co/datasets/parler-tts/mls-eng-10k-tags_tagged_10k_generated).
+
+
+## 3. Training
+
+The script [`run_parler_tts_training.py`](/training/run_parler_tts_training.py) is an end-to-end script that:
+1. load dataset(s) and merge them to the annotation dataset(s) if necessary
+2. pre-compute audio tokens
+3. train Parler-TTS
+
+To train Parler-TTS Mini v0.1, we roughly used:
+
+```sh
+accelerate launch ./training/run_parler_tts_training.py \
+    --model_name_or_path "./parler-tts-untrained-600M/parler-tts-untrained-600M/" \
+    --feature_extractor_name "parler-tts/dac_44khZ_8kbps" \
+    --description_tokenizer_name "google/flan-t5-base" \
+    --prompt_tokenizer_name "google/flan-t5-base" \
+    --report_to "wandb" \
+    --overwrite_output_dir true \
+    --train_dataset_name "blabble-io/libritts_r+blabble-io/libritts_r+blabble-io/libritts_r+parler-tts/mls_eng_10k" \
+    --train_metadata_dataset_name "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated" \
+    --train_dataset_config_name "clean+clean+other+default" \
+    --train_split_name "train.clean.360+train.clean.100+train.other.500+train" \
+    --eval_dataset_name "blabble-io/libritts_r+parler-tts/mls_eng_10k" \
+    --eval_metadata_dataset_name "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated" \
+    --eval_dataset_config_name "other+default" \
+    --eval_split_name "test.other+test" \
+    --target_audio_column_name "audio" \
+    --description_column_name "text_description" \
+    --prompt_column_name "text" \
+    --max_duration_in_seconds 30 \
+    --min_duration_in_seconds 2.0 \
+    --max_text_length 400 \
+    --add_audio_samples_to_wandb true \
+    --id_column_name "id" \
+    --preprocessing_num_workers 8 \
+    --do_train true \
+    --num_train_epochs 40 \
+    --gradient_accumulation_steps 8 \
+    --gradient_checkpointing false \
+    --per_device_train_batch_size 3 \
+    --learning_rate 0.00095 \
+    --adam_beta1 0.9 \
+    --adam_beta2 0.99 \
+    --weight_decay 0.01 \
+    --lr_scheduler_type "constant_with_warmup" \
+    --warmup_steps 20000 \
+    --logging_steps 1000 \
+    --freeze_text_encoder true \
+    --do_eval true \
+    --predict_with_generate true \
+    --include_inputs_for_metrics true \
+    --evaluation_strategy steps \
+    --eval_steps 10000 \
+    --save_steps 10000 \
+    --per_device_eval_batch_size 12 \
+    --audio_encoder_per_device_batch_size 20 \
+    --dtype "bfloat16" \
+    --seed 456 \
+    --output_dir "./output_dir_training/" \
+    --temporary_save_to_disk "./audio_code_tmp/" \
+    --save_to_disk "./tmp_dataset_audio/" \
+    --max_eval_samples 96 \
+    --dataloader_num_workers 8 \
+    --group_by_length true
+```
+
+In particular, note how multiple training datasets, metadataset, configurations and splits can be loaded by separating the dataset arguments by + symbols:
+```sh
+    "train_dataset_name": "blabble-io/libritts_r+blabble-io/libritts_r+blabble-io/libritts_r+parler-tts/mls_eng_10k",
+    "train_metadata_dataset_name": "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated",
+    "train_dataset_config_name": "clean+clean+other+default",
+    "train_split_name": "train.clean.360+train.clean.100+train.other.500+train",
+```
+
+
+Additionally, you can also write a JSON config file. Here, [starting_point_0.01.json](helpers/training_configs/starting_point_0.01.json) contains the exact same hyper-parameters than above and can be launched like that:
+```sh
+accelerate launch ./training/run_parler_tts_training.py ./helpers/training_configs/starting_point_0.01.json
+```
+
+Training logs will be reported to wandb, provided that you passed `--report_to "wandb"` to the arguments. An example of what a training log from the above training looks like can be found [here](https://wandb.ai/ylacombe/parler-tts-300M-punctuated/runs/q6h7hspc?nw=nwuserylacombe).
+
+> [!TIP]
+> Starting training a new model from scratch can easily be overwhelming, so here's what training looked like for v0.1: [logs](https://api.wandb.ai/links/ylacombe/ea449l81)
+
+Scaling to multiple GPUs using [distributed data parallelism (DDP)](https://pytorch.org/tutorials/beginner/ddp_series_theory.html) is trivial: simply run `accelerate config` and select the multi-GPU option, specifying the IDs of the GPUs you wish to use. The above script can then be run using DDP with no code changes. In our case, we used a node of 8 H100 80GB to train Parler-TTS v0.1 for around 4 days.
+
+
+There are a few other noteworthy arguments:
+1. `train_metadata_dataset_name` and `eval_metadata_dataset_name` specify, if necessary, the names of the dataset(s) that contain(s) the conditionning text descriptions. For example, this [dataset resulting from the Data-Speech annotation process](https://huggingface.co/datasets/parler-tts/libritts_r_tags_tagged_10k_generated) is saved without the audio column, as it's costly to write and push audio data, so it needs to be concatenated back to the original LibriTTS-R dataset.
+2. As noted above, the script pre-computes audio tokens as computing audio codes is costly and only needs to be done once, since we're freezing the audio encoder. `audio_encoder_per_device_batch_size` is used to precise the per devie batch size for this pre-processing step.
+3. Additionnally, when scaling up the training data and iterating on the hyper-parameters or the model architecture, we might want to avoid recomputing the audio tokens at each training run. That's why we introduced two additional parameters, `save_to_disk` and `temporary_save_to_disk` that serves as temporary buffers to save intermediary datasets. Note that processed data is made of text and audio tokens which are much more memory efficient, so the additional required space is negligible.
+4. `predict_with_generate` and `add_audio_samples_to_wandb` are required to store generated audios and to compute WER and CLAP similarity.
+5. `freeze_text_encoder`: which allows to freeze the text encoder, to save compute resources.
+
+And finally, two additional comments:
+1. `lr_scheduler_stype`: defines the learning rate schedule, one of `constant_with_warmup` or `cosine`. When experimenting with a training set-up or training for very few epochs, using `constant_with_warmup` is typically beneficial, since the learning rate remains high over the short training run. When performing longer training runs, using a `cosine` schedule shoud give better results.
+2. `dtype`: data type (dtype) in which the model computation should be performed. Note that this only controls the dtype of the computations (forward and backward pass), and not the dtype of the parameters or optimiser states.
+
+> [!TIP]
+> Fine-tuning is as easy as modifying `model_name_or_path` to a pre-trained model.
+> For example: `--model_name_or_path parler-tts/parler_tts_mini_v0.1`.