End of training

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+datasets:
+- vivos
+metrics:
+- wer
+model-index:
+- name: working
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: vivos
+      type: vivos
+      config: default
+      split: None
+      args: default
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.1690242779130206
+---
+
+<!-- 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. -->
+
+# working
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the vivos dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2700
+- Wer: 0.1690
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.2111        | 2.0   | 292  | 0.9069          | 0.5315 |
+| 0.6195        | 4.0   | 584  | 0.4762          | 0.3436 |
+| 0.4338        | 6.0   | 876  | 0.3627          | 0.2657 |
+| 0.3471        | 8.0   | 1168 | 0.4132          | 0.2817 |
+| 0.2897        | 10.0  | 1460 | 0.3098          | 0.2178 |
+| 0.2471        | 12.0  | 1752 | 0.2761          | 0.1957 |
+| 0.2184        | 14.0  | 2044 | 0.2694          | 0.1807 |
+| 0.1927        | 16.0  | 2336 | 0.2705          | 0.1753 |
+| 0.1754        | 18.0  | 2628 | 0.2692          | 0.1709 |
+| 0.1622        | 20.0  | 2920 | 0.2700          | 0.1690 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

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": 0.0,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "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": 91,
+  "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": "4.42.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 94,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e48d211eaeace563dc663cd882a1325341dec18b4cb922bb8b127d76f1f72e9
+size 377801840

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015bf27299727cb517cbd71351b1aa4b2c9d1baed92355839627001641b64d3b
+size 5112

vocab.json

@@ -0,0 +1 @@
+{"A": 1, "B": 2, "C": 3, "D": 4, "E": 5, "G": 6, "H": 7, "I": 8, "K": 9, "L": 10, "M": 11, "N": 12, "O": 13, "P": 14, "Q": 15, "R": 16, "S": 17, "T": 18, "U": 19, "V": 20, "X": 21, "Y": 22, "\u00c0": 23, "\u00c1": 24, "\u00c2": 25, "\u00c3": 26, "\u00c8": 27, "\u00c9": 28, "\u00ca": 29, "\u00cc": 30, "\u00cd": 31, "\u00d2": 32, "\u00d3": 33, "\u00d4": 34, "\u00d5": 35, "\u00d9": 36, "\u00da": 37, "\u00dd": 38, "\u0102": 39, "\u0110": 40, "\u0128": 41, "\u0168": 42, "\u01a0": 43, "\u01af": 44, "\u1ea0": 45, "\u1ea2": 46, "\u1ea4": 47, "\u1ea6": 48, "\u1ea8": 49, "\u1eaa": 50, "\u1eac": 51, "\u1eae": 52, "\u1eb0": 53, "\u1eb2": 54, "\u1eb4": 55, "\u1eb6": 56, "\u1eb8": 57, "\u1eba": 58, "\u1ebc": 59, "\u1ebe": 60, "\u1ec0": 61, "\u1ec2": 62, "\u1ec4": 63, "\u1ec6": 64, "\u1ec8": 65, "\u1eca": 66, "\u1ecc": 67, "\u1ece": 68, "\u1ed0": 69, "\u1ed2": 70, "\u1ed4": 71, "\u1ed6": 72, "\u1ed8": 73, "\u1eda": 74, "\u1edc": 75, "\u1ede": 76, "\u1ee0": 77, "\u1ee2": 78, "\u1ee4": 79, "\u1ee6": 80, "\u1ee8": 81, "\u1eea": 82, "\u1eec": 83, "\u1eee": 84, "\u1ef0": 85, "\u1ef2": 86, "\u1ef4": 87, "\u1ef6": 88, "\u1ef8": 89, "|": 0, "[UNK]": 90, "[PAD]": 91}