End of training

README.md

@@ -0,0 +1,107 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
+tags:
+- generated_from_trainer
+datasets:
+- timit_asr
+metrics:
+- wer
+model-index:
+- name: timit-xls-r-300m
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: timit_asr
+      type: timit_asr
+      config: clean
+      split: None
+      args: clean
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.2466404796361381
+---
+
+<!-- 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. -->
+
+# timit-xls-r-300m
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the timit_asr dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4457
+- Wer: 0.2466
+
+## 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
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 4.0049        | 1.72  | 500   | 1.9735          | 1.0655 |
+| 1.033         | 3.45  | 1000  | 0.6172          | 0.5115 |
+| 0.4499        | 5.17  | 1500  | 0.5231          | 0.4395 |
+| 0.2551        | 6.9   | 2000  | 0.4768          | 0.3772 |
+| 0.1724        | 8.62  | 2500  | 0.4699          | 0.3626 |
+| 0.133         | 10.34 | 3000  | 0.4346          | 0.3329 |
+| 0.1082        | 12.07 | 3500  | 0.4479          | 0.3163 |
+| 0.0886        | 13.79 | 4000  | 0.4393          | 0.3167 |
+| 0.0766        | 15.52 | 4500  | 0.4920          | 0.3100 |
+| 0.0637        | 17.24 | 5000  | 0.4510          | 0.3013 |
+| 0.0607        | 18.97 | 5500  | 0.4284          | 0.2808 |
+| 0.0495        | 20.69 | 6000  | 0.4270          | 0.2820 |
+| 0.0479        | 22.41 | 6500  | 0.4294          | 0.2852 |
+| 0.0444        | 24.14 | 7000  | 0.4456          | 0.2816 |
+| 0.0378        | 25.86 | 7500  | 0.4236          | 0.2763 |
+| 0.0325        | 27.59 | 8000  | 0.4365          | 0.2849 |
+| 0.031         | 29.31 | 8500  | 0.4482          | 0.2862 |
+| 0.0285        | 31.03 | 9000  | 0.4388          | 0.2691 |
+| 0.0252        | 32.76 | 9500  | 0.4253          | 0.2692 |
+| 0.0229        | 34.48 | 10000 | 0.4598          | 0.2641 |
+| 0.0223        | 36.21 | 10500 | 0.4462          | 0.2533 |
+| 0.0188        | 37.93 | 11000 | 0.4350          | 0.2673 |
+| 0.0163        | 39.66 | 11500 | 0.4460          | 0.2608 |
+| 0.0167        | 41.38 | 12000 | 0.4441          | 0.2683 |
+| 0.0138        | 43.1  | 12500 | 0.4290          | 0.2528 |
+| 0.0127        | 44.83 | 13000 | 0.4360          | 0.2508 |
+| 0.0124        | 46.55 | 13500 | 0.4406          | 0.2511 |
+| 0.0107        | 48.28 | 14000 | 0.4482          | 0.2477 |
+| 0.0108        | 50.0  | 14500 | 0.4457          | 0.2466 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.0.1+cu117
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "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": 0.0,
+  "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": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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,
+  "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": 29,
+  "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": "4.39.3",
+  "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:b801c28152a4a7425a3425f091dc8de860fe34512085c8f545680983b1c7803c
+size 1261938632

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": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364de5a46e356417562c7ea068418040c4949aaec5037d8c39d29d2d20a9535a
+size 4475