HuBERT_fine_golos

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_13_0
+metrics:
+- wer
+model-index:
+- name: model_finetuned
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_13_0
+      type: common_voice_13_0
+      config: ru
+      split: test
+      args: ru
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.5240747438215793
+---
+
+<!-- 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. -->
+
+# model_finetuned
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4337
+- Wer: 0.5241
+
+## 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: 0.0003
+- train_batch_size: 24
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer    |
+|:-------------:|:-------:|:----:|:---------------:|:------:|
+| 5.1665        | 1.9139  | 400  | 1.3007          | 0.9612 |
+| 0.9389        | 3.8278  | 800  | 0.6428          | 0.7616 |
+| 0.5785        | 5.7416  | 1200 | 0.5126          | 0.6447 |
+| 0.4408        | 7.6555  | 1600 | 0.4807          | 0.5937 |
+| 0.3589        | 9.5694  | 2000 | 0.4581          | 0.5665 |
+| 0.3033        | 11.4833 | 2400 | 0.4461          | 0.5416 |
+| 0.2678        | 13.3971 | 2800 | 0.4337          | 0.5241 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 37,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 38,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9575e91fb23ef07a582a503fb56459e835d65bbb13b4d9c1bbcf44b291f63eaa
+size 1261963280

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Jun27_10-40-23_a746c8b6ec1b/events.out.tfevents.1719484838.a746c8b6ec1b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb36d3d653fba7aa038d935da88af996c96854c37235dd1a39293d7e4de21752
+size 10547

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df2e5ad1a1e8490b6bfbc75abca625ec853ded5bf5ca334f52d22fb1f2ed816
+size 5112