End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-small-br
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# whisper-small-br
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5767
+- Wer: 39.9748
+- Cer: 15.0329
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- training_steps: 4000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     | Cer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 0.782         | 0.58  | 500  | 0.7847          | 61.4497 | 24.5285 |
+| 0.3209        | 1.16  | 1000 | 0.6244          | 47.0028 | 17.7797 |
+| 0.3041        | 1.74  | 1500 | 0.5578          | 45.1182 | 18.4874 |
+| 0.1177        | 2.33  | 2000 | 0.5479          | 42.1620 | 16.4081 |
+| 0.1234        | 2.91  | 2500 | 0.5353          | 41.6136 | 15.9008 |
+| 0.0371        | 3.49  | 3000 | 0.5593          | 39.1428 | 14.7689 |
+| 0.02          | 4.07  | 3500 | 0.5714          | 38.8591 | 14.7176 |
+| 0.0115        | 4.65  | 4000 | 0.5767          | 39.9748 | 15.0329 |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.18.0
+- Tokenizers 0.15.2

bck-checkpoint-3500/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

bck-checkpoint-3500/generation_config.json

@@ -0,0 +1,266 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "breton",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.39.1"
+}

bck-checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df77e3bda800c7d644d885a1d1ed62588d30ce79964f489153557d0f3bc22bc4
+size 966995080

bck-checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b442570c163e08d67c2ac084ad1a650a8c4dcbc23c52037ba2a924c26015f53
+size 1925063607

bck-checkpoint-3500/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

bck-checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3a77fa271e382167ede871e69b26f480319be2b7af14900871ec0a2e39e43a
+size 14575

bck-checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52db84bc37411d48adce43568dbf28a2c86b3c5a86cdc3dd9cd4593f0b5c7689
+size 627

bck-checkpoint-3500/trainer_state.json

@@ -0,0 +1,336 @@
+{
+  "best_metric": 43.19571383548692,
+  "best_model_checkpoint": "whisper-small-br/checkpoint-3500",
+  "epoch": 4.069767441860465,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "grad_norm": 23.873233795166016,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 4.4977,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 18.380311965942383,
+      "learning_rate": 9.75e-06,
+      "loss": 2.0428,
+      "step": 200
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 15.277495384216309,
+      "learning_rate": 9.75e-06,
+      "loss": 1.282,
+      "step": 300
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 16.010156631469727,
+      "learning_rate": 9.486842105263158e-06,
+      "loss": 0.9714,
+      "step": 400
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 12.95919418334961,
+      "learning_rate": 9.223684210526316e-06,
+      "loss": 0.8721,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "eval_cer": 23.931937364773187,
+      "eval_loss": 0.847813606262207,
+      "eval_runtime": 707.7025,
+      "eval_samples_per_second": 3.613,
+      "eval_steps_per_second": 0.452,
+      "eval_wer": 62.74188465174914,
+      "step": 500
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 15.317465782165527,
+      "learning_rate": 8.960526315789474e-06,
+      "loss": 0.8022,
+      "step": 600
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 14.4519624710083,
+      "learning_rate": 8.697368421052633e-06,
+      "loss": 0.7294,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 13.281527519226074,
+      "learning_rate": 8.43421052631579e-06,
+      "loss": 0.7037,
+      "step": 800
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 11.638937950134277,
+      "learning_rate": 8.171052631578949e-06,
+      "loss": 0.5775,
+      "step": 900
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 10.528143882751465,
+      "learning_rate": 7.907894736842105e-06,
+      "loss": 0.413,
+      "step": 1000
+    },
+    {
+      "epoch": 1.16,
+      "eval_cer": 20.239099343576957,
+      "eval_loss": 0.6627262830734253,
+      "eval_runtime": 694.5097,
+      "eval_samples_per_second": 3.682,
+      "eval_steps_per_second": 0.461,
+      "eval_wer": 51.78695241096754,
+      "step": 1000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 11.562024116516113,
+      "learning_rate": 7.644736842105264e-06,
+      "loss": 0.4373,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.719500541687012,
+      "learning_rate": 7.381578947368422e-06,
+      "loss": 0.4028,
+      "step": 1200
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 11.709799766540527,
+      "learning_rate": 7.11842105263158e-06,
+      "loss": 0.4085,
+      "step": 1300
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 10.174458503723145,
+      "learning_rate": 6.855263157894737e-06,
+      "loss": 0.394,
+      "step": 1400
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 10.892149925231934,
+      "learning_rate": 6.5921052631578955e-06,
+      "loss": 0.3822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.74,
+      "eval_cer": 17.72097742246996,
+      "eval_loss": 0.6052409410476685,
+      "eval_runtime": 688.7859,
+      "eval_samples_per_second": 3.712,
+      "eval_steps_per_second": 0.465,
+      "eval_wer": 46.448156318941066,
+      "step": 1500
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 12.372304916381836,
+      "learning_rate": 6.328947368421054e-06,
+      "loss": 0.3767,
+      "step": 1600
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 13.72421646118164,
+      "learning_rate": 6.065789473684212e-06,
+      "loss": 0.3938,
+      "step": 1700
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 10.771753311157227,
+      "learning_rate": 5.802631578947368e-06,
+      "loss": 0.2385,
+      "step": 1800
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 5.737514495849609,
+      "learning_rate": 5.5394736842105266e-06,
+      "loss": 0.1885,
+      "step": 1900
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 6.4449920654296875,
+      "learning_rate": 5.276315789473685e-06,
+      "loss": 0.1868,
+      "step": 2000
+    },
+    {
+      "epoch": 2.33,
+      "eval_cer": 17.650078844108695,
+      "eval_loss": 0.5885388255119324,
+      "eval_runtime": 693.9092,
+      "eval_samples_per_second": 3.685,
+      "eval_steps_per_second": 0.461,
+      "eval_wer": 45.30728017648913,
+      "step": 2000
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 7.215250015258789,
+      "learning_rate": 5.013157894736842e-06,
+      "loss": 0.1873,
+      "step": 2100
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 6.823380947113037,
+      "learning_rate": 4.75e-06,
+      "loss": 0.1898,
+      "step": 2200
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 7.433701992034912,
+      "learning_rate": 4.4868421052631584e-06,
+      "loss": 0.1801,
+      "step": 2300
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 8.947402000427246,
+      "learning_rate": 4.223684210526316e-06,
+      "loss": 0.1911,
+      "step": 2400
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 4.656549453735352,
+      "learning_rate": 3.960526315789474e-06,
+      "loss": 0.1956,
+      "step": 2500
+    },
+    {
+      "epoch": 2.91,
+      "eval_cer": 16.69661520407789,
+      "eval_loss": 0.5721948146820068,
+      "eval_runtime": 688.2161,
+      "eval_samples_per_second": 3.715,
+      "eval_steps_per_second": 0.465,
+      "eval_wer": 43.98361172392058,
+      "step": 2500
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 5.275825023651123,
+      "learning_rate": 3.6973684210526317e-06,
+      "loss": 0.1568,
+      "step": 2600
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 3.9346418380737305,
+      "learning_rate": 3.43421052631579e-06,
+      "loss": 0.0884,
+      "step": 2700
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 8.16520881652832,
+      "learning_rate": 3.1710526315789477e-06,
+      "loss": 0.0893,
+      "step": 2800
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 9.721732139587402,
+      "learning_rate": 2.907894736842106e-06,
+      "loss": 0.0893,
+      "step": 2900
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 4.916592597961426,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.0814,
+      "step": 3000
+    },
+    {
+      "epoch": 3.49,
+      "eval_cer": 17.04132898162749,
+      "eval_loss": 0.5933119058609009,
+      "eval_runtime": 688.3586,
+      "eval_samples_per_second": 3.715,
+      "eval_steps_per_second": 0.465,
+      "eval_wer": 44.28616451307911,
+      "step": 3000
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 5.402080535888672,
+      "learning_rate": 2.381578947368421e-06,
+      "loss": 0.0847,
+      "step": 3100
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 4.390013694763184,
+      "learning_rate": 2.118421052631579e-06,
+      "loss": 0.0902,
+      "step": 3200
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 3.571608543395996,
+      "learning_rate": 1.855263157894737e-06,
+      "loss": 0.0757,
+      "step": 3300
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 6.823545455932617,
+      "learning_rate": 1.5921052631578949e-06,
+      "loss": 0.0811,
+      "step": 3400
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 2.958061933517456,
+      "learning_rate": 1.3289473684210526e-06,
+      "loss": 0.0554,
+      "step": 3500
+    },
+    {
+      "epoch": 4.07,
+      "eval_cer": 16.441135844120918,
+      "eval_loss": 0.6083739399909973,
+      "eval_runtime": 690.4893,
+      "eval_samples_per_second": 3.703,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 43.19571383548692,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8.0746195009536e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

bck-checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6b96e02caa3728fdbe69b1b53c129d42b7cf7db2b7fa3d6c5dece5dcba33f8
+size 4667

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-base",
+  "_name_or_path": "openai/whisper-small",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -13,17 +13,17 @@
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 512,
-  "decoder_attention_heads": 8,
-  "decoder_ffn_dim": 2048,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 12,
   "eos_token_id": 50257,
   "forced_decoder_ids": null,
   "init_std": 0.02,
@@ -39,14 +39,14 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
-  "use_cache": true,
+  "transformers_version": "4.39.1",
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

generation_config.json

@@ -0,0 +1,266 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "breton",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.39.1"
+}

merges.txt

@@ -1,4 +1,5 @@
 #version: 0.2
+Ġ t
 Ġ a
 Ġt h
 i n

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f241bc8c2b1789113b10be95fda8d4090543330e87fed0bb66bac16a607d8cb
-size 290403936
+oid sha256:aeeef5fbd5d40b26b8e943b19f39f76e4bb8a455d0e7f642ac1ba51dc5e4bd69
+size 966995080

runs/Aug20_21-41-26_gweltaz-NUC10i7FNK/events.out.tfevents.1724182888.gweltaz-NUC10i7FNK.3502.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620ac5e92d2fc446c799558e8026bc5e456bebd2365e90ff6c658f7fc4e7089e
+size 17166

runs/Aug21_09-51-18_gweltaz-NUC10i7FNK/events.out.tfevents.1724226679.gweltaz-NUC10i7FNK.7651.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71625f72c3cfa7a64e459283b1dbee14c60402a91bd9fbf689c99cc9b9f81663
+size 17166

special_tokens_map.json

@@ -111,14 +111,14 @@
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -132,7 +132,7 @@
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -5,7 +5,7 @@
     "50257": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12980,7 +12980,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "model_max_length": 448,
+  "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "processor_class": "WhisperProcessor",
   "return_attention_mask": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2e73cdda8257333a1ff484734cbec89e0eac555048409375d15fcadc3075bf
-size 4728
+oid sha256:61e6ce06127f678cc499816e943dbf33660aa9806bdbf3007ca58d9efda9f324
+size 4667