End of training

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-base-timit-demo-google-colab
+  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. -->
+
+# wav2vec2-base-timit-demo-google-colab
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5313
+- Wer: 0.3317
+
+## 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: 0.0001
+- 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: 1000
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 3.5823        | 1.0   | 500   | 1.8501          | 1.0236 |
+| 0.8931        | 2.01  | 1000  | 0.5018          | 0.5196 |
+| 0.4269        | 3.01  | 1500  | 0.4266          | 0.4461 |
+| 0.2876        | 4.02  | 2000  | 0.4458          | 0.4359 |
+| 0.2272        | 5.02  | 2500  | 0.4183          | 0.4146 |
+| 0.1813        | 6.02  | 3000  | 0.4151          | 0.3945 |
+| 0.1555        | 7.03  | 3500  | 0.4216          | 0.3881 |
+| 0.1353        | 8.03  | 4000  | 0.4282          | 0.3824 |
+| 0.1221        | 9.04  | 4500  | 0.4848          | 0.3845 |
+| 0.1135        | 10.04 | 5000  | 0.5003          | 0.3818 |
+| 0.0968        | 11.04 | 5500  | 0.5331          | 0.3738 |
+| 0.09          | 12.05 | 6000  | 0.5082          | 0.3690 |
+| 0.084         | 13.05 | 6500  | 0.4573          | 0.3634 |
+| 0.0744        | 14.06 | 7000  | 0.4711          | 0.3705 |
+| 0.0663        | 15.06 | 7500  | 0.4955          | 0.3634 |
+| 0.0612        | 16.06 | 8000  | 0.4721          | 0.3558 |
+| 0.0535        | 17.07 | 8500  | 0.4965          | 0.3654 |
+| 0.0527        | 18.07 | 9000  | 0.5381          | 0.3592 |
+| 0.0458        | 19.08 | 9500  | 0.5029          | 0.3498 |
+| 0.0424        | 20.08 | 10000 | 0.5814          | 0.3547 |
+| 0.042         | 21.08 | 10500 | 0.4893          | 0.3480 |
+| 0.0373        | 22.09 | 11000 | 0.5047          | 0.3482 |
+| 0.0333        | 23.09 | 11500 | 0.5235          | 0.3426 |
+| 0.0306        | 24.1  | 12000 | 0.5165          | 0.3472 |
+| 0.0293        | 25.1  | 12500 | 0.4988          | 0.3426 |
+| 0.025         | 26.1  | 13000 | 0.5157          | 0.3382 |
+| 0.0255        | 27.11 | 13500 | 0.5278          | 0.3412 |
+| 0.022         | 28.11 | 14000 | 0.5401          | 0.3364 |
+| 0.0195        | 29.12 | 14500 | 0.5313          | 0.3317 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 1.18.3
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "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": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 29,
+  "proj_codevector_dim": 256,
+  "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": "4.35.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df59320d9b8874f1d3eda974e16dedf9bae3496f762c9fa42eb92412c8c56bd
+size 377611120

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Feb08_10-15-21_efe51ae7237c/events.out.tfevents.1707387401.efe51ae7237c.3846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cd0ca9d2ab3cb9787832730bb2788cca830dbd12a79df4aa65f7539d0e3732
+size 20105

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21db2c945ad27587c093c2f18afbf62bd6db9ba9a0b98514635abbb6d89776ad
+size 4600