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: 0.5328
+- Wer: 0.2175
+
+## 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    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 3.4608        | 1.0   | 500   | 1.4610          | 0.9290 |
+| 0.796         | 2.01  | 1000  | 0.5283          | 0.4217 |
+| 0.4219        | 3.01  | 1500  | 0.4277          | 0.3353 |
+| 0.2919        | 4.02  | 2000  | 0.4154          | 0.3102 |
+| 0.2263        | 5.02  | 2500  | 0.4096          | 0.2954 |
+| 0.1885        | 6.02  | 3000  | 0.4274          | 0.2944 |
+| 0.1595        | 7.03  | 3500  | 0.4529          | 0.2681 |
+| 0.1371        | 8.03  | 4000  | 0.4309          | 0.2721 |
+| 0.1218        | 9.04  | 4500  | 0.4574          | 0.2629 |
+| 0.1118        | 10.04 | 5000  | 0.5396          | 0.2605 |
+| 0.0988        | 11.04 | 5500  | 0.5031          | 0.2683 |
+| 0.0944        | 12.05 | 6000  | 0.5040          | 0.2595 |
+| 0.0781        | 13.05 | 6500  | 0.4909          | 0.2611 |
+| 0.0714        | 14.06 | 7000  | 0.4740          | 0.2635 |
+| 0.0648        | 15.06 | 7500  | 0.4613          | 0.2509 |
+| 0.0628        | 16.06 | 8000  | 0.4731          | 0.2508 |
+| 0.0539        | 17.07 | 8500  | 0.5100          | 0.2448 |
+| 0.0542        | 18.07 | 9000  | 0.5048          | 0.2507 |
+| 0.0453        | 19.08 | 9500  | 0.5290          | 0.2466 |
+| 0.0446        | 20.08 | 10000 | 0.5482          | 0.2398 |
+| 0.0405        | 21.08 | 10500 | 0.5768          | 0.2422 |
+| 0.0368        | 22.09 | 11000 | 0.5848          | 0.2403 |
+| 0.0349        | 23.09 | 11500 | 0.5469          | 0.2321 |
+| 0.0326        | 24.1  | 12000 | 0.5618          | 0.2294 |
+| 0.028         | 25.1  | 12500 | 0.5590          | 0.2297 |
+| 0.0254        | 26.1  | 13000 | 0.5531          | 0.2291 |
+| 0.0258        | 27.11 | 13500 | 0.5302          | 0.2215 |
+| 0.0244        | 28.11 | 14000 | 0.5388          | 0.2188 |
+| 0.0195        | 29.12 | 14500 | 0.5328          | 0.2175 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 1.18.3
+- Tokenizers 0.15.0

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:b90377e74b16daae1cae2f17a6e22a874a83523d285f70a0ffb540c94275b83c
+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/Dec13_22-10-57_a635b3983843/events.out.tfevents.1702505564.a635b3983843.357.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576339a4e74d504593bb0fedceab8f65e105127587d4084fde16b84bc5aa8a03
+size 20105

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5167de2cf54f0fd0733f314dd00b469adc591b63273e40d3b27e2ac9d04097
+size 4600