End of training

README.md

@@ -0,0 +1,104 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-timit-xls-r-300m-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-timit-xls-r-300m-colab
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3293
+- Wer: 0.2879
+- Cer: 0.0927
+
+## 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
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| No log        | 0.69  | 400   | 3.1501          | 1.0    | 0.9865 |
+| 4.3829        | 1.38  | 800   | 2.9694          | 1.0    | 0.9865 |
+| 2.6389        | 2.08  | 1200  | 0.6558          | 0.5876 | 0.1878 |
+| 0.9293        | 2.77  | 1600  | 0.4232          | 0.4722 | 0.1462 |
+| 0.5686        | 3.46  | 2000  | 0.3513          | 0.4118 | 0.1279 |
+| 0.5686        | 4.15  | 2400  | 0.3246          | 0.3994 | 0.1227 |
+| 0.4388        | 4.84  | 2800  | 0.3037          | 0.3716 | 0.1158 |
+| 0.3431        | 5.54  | 3200  | 0.3055          | 0.3674 | 0.1158 |
+| 0.3164        | 6.23  | 3600  | 0.2973          | 0.3589 | 0.1128 |
+| 0.2678        | 6.92  | 4000  | 0.3053          | 0.3421 | 0.1080 |
+| 0.2678        | 7.61  | 4400  | 0.3058          | 0.3435 | 0.1083 |
+| 0.2376        | 8.3   | 4800  | 0.3144          | 0.3408 | 0.1094 |
+| 0.2199        | 9.0   | 5200  | 0.3177          | 0.3371 | 0.1052 |
+| 0.1988        | 9.69  | 5600  | 0.3123          | 0.3299 | 0.1057 |
+| 0.1816        | 10.38 | 6000  | 0.2918          | 0.3282 | 0.1049 |
+| 0.1816        | 11.07 | 6400  | 0.3195          | 0.3270 | 0.1049 |
+| 0.1652        | 11.76 | 6800  | 0.3080          | 0.3280 | 0.1056 |
+| 0.1576        | 12.46 | 7200  | 0.2859          | 0.3218 | 0.1031 |
+| 0.1558        | 13.15 | 7600  | 0.3143          | 0.3179 | 0.1018 |
+| 0.1411        | 13.84 | 8000  | 0.3354          | 0.3171 | 0.1045 |
+| 0.1411        | 14.53 | 8400  | 0.3285          | 0.3149 | 0.1018 |
+| 0.1381        | 15.22 | 8800  | 0.3048          | 0.3138 | 0.1010 |
+| 0.1178        | 15.92 | 9200  | 0.3421          | 0.3140 | 0.1012 |
+| 0.1182        | 16.61 | 9600  | 0.3258          | 0.3109 | 0.1001 |
+| 0.1131        | 17.3  | 10000 | 0.3220          | 0.3120 | 0.1002 |
+| 0.1131        | 17.99 | 10400 | 0.3156          | 0.3098 | 0.0991 |
+| 0.1031        | 18.69 | 10800 | 0.3198          | 0.3062 | 0.0980 |
+| 0.1023        | 19.38 | 11200 | 0.3227          | 0.3021 | 0.0972 |
+| 0.0959        | 20.07 | 11600 | 0.3187          | 0.3025 | 0.0973 |
+| 0.0881        | 20.76 | 12000 | 0.3177          | 0.3004 | 0.0965 |
+| 0.0881        | 21.45 | 12400 | 0.3435          | 0.2976 | 0.0960 |
+| 0.0919        | 22.15 | 12800 | 0.3142          | 0.2958 | 0.0954 |
+| 0.0787        | 22.84 | 13200 | 0.3010          | 0.3000 | 0.0970 |
+| 0.0794        | 23.53 | 13600 | 0.3528          | 0.3008 | 0.0973 |
+| 0.0751        | 24.22 | 14000 | 0.3352          | 0.2954 | 0.0961 |
+| 0.0751        | 24.91 | 14400 | 0.3314          | 0.2977 | 0.0963 |
+| 0.0778        | 25.61 | 14800 | 0.3214          | 0.2955 | 0.0953 |
+| 0.0711        | 26.3  | 15200 | 0.3277          | 0.2936 | 0.0944 |
+| 0.0681        | 26.99 | 15600 | 0.3237          | 0.2915 | 0.0940 |
+| 0.0682        | 27.68 | 16000 | 0.3284          | 0.2918 | 0.0943 |
+| 0.0682        | 28.37 | 16400 | 0.3304          | 0.2904 | 0.0933 |
+| 0.0731        | 29.07 | 16800 | 0.3307          | 0.2881 | 0.0927 |
+| 0.0619        | 29.76 | 17200 | 0.3293          | 0.2879 | 0.0927 |
+
+
+### Framework versions
+
+- Transformers 4.32.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 1.18.3
+- Tokenizers 0.13.3

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": 0.1,
+  "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": 0.1,
+  "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_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": 0.075,
+  "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": "4.32.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10513426a776859d1c335d1aa5eff465ef984c388caaeb1dd6c9d4ba5be6d319
+size 1262033069

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0bce3ffac8d15ff015bb30f76361865cce76bacab2ad18c912392df5aa85be4
+size 4027