updating wav2vec base with correct model files

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: pidgin-wav2vec2-base-960h
+  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. -->
+
+# pidgin-wav2vec2-base-960h
+
+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: 1.0898
+- Wer: 0.3966
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 3407
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 4.3949        | 1.48  | 500   | 3.3325          | 0.9999 |
+| 2.4656        | 2.95  | 1000  | 1.4727          | 0.8026 |
+| 1.1896        | 4.43  | 1500  | 1.0925          | 0.6252 |
+| 0.8558        | 5.91  | 2000  | 0.9467          | 0.5422 |
+| 0.6427        | 7.39  | 2500  | 0.9856          | 0.5096 |
+| 0.5371        | 8.86  | 3000  | 0.9794          | 0.5093 |
+| 0.4553        | 10.34 | 3500  | 0.8719          | 0.4641 |
+| 0.3921        | 11.82 | 4000  | 0.9344          | 0.4566 |
+| 0.3406        | 13.29 | 4500  | 1.0211          | 0.4550 |
+| 0.3046        | 14.77 | 5000  | 0.8668          | 0.4423 |
+| 0.2651        | 16.25 | 5500  | 1.0384          | 0.4261 |
+| 0.244         | 17.73 | 6000  | 1.0437          | 0.4296 |
+| 0.2203        | 19.2  | 6500  | 0.9244          | 0.4228 |
+| 0.1995        | 20.68 | 7000  | 0.9832          | 0.4165 |
+| 0.1838        | 22.16 | 7500  | 1.1455          | 0.4112 |
+| 0.1632        | 23.63 | 8000  | 1.1102          | 0.4102 |
+| 0.1576        | 25.11 | 8500  | 1.0769          | 0.4044 |
+| 0.1388        | 26.59 | 9000  | 1.1008          | 0.4013 |
+| 0.1346        | 28.06 | 9500  | 1.0940          | 0.4000 |
+| 0.1204        | 29.54 | 10000 | 1.0898          | 0.3966 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.15.2

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": true,
+  "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": 44,
+  "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": "4.37.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 45,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1f5473d9c1d165b1a03694d2dd6b4227bd08b9419b41fa2bcd332eecae972c
+size 377651060

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:b96a8547ec93febb076a78b0510127048084853295c74310e5985fa39ded13f0
+size 4347

vocab.json

@@ -0,0 +1 @@
+{"g": 0, "/": 1, "e": 2, "0": 3, "'": 4, "x": 5, "\u00e7": 6, "\u00e9": 7, "q": 8, "v": 9, "z": 10, "\u00e8": 11, "5": 12, "d": 13, "6": 14, "f": 15, "c": 16, "@": 17, "t": 18, "i": 20, "o": 21, "2": 22, "a": 23, "b": 24, "h": 25, "8": 26, "p": 27, "4": 28, "r": 29, "w": 30, "7": 31, "k": 32, "j": 33, "1": 34, "y": 35, "s": 36, "m": 37, "u": 38, "9": 39, "l": 40, "3": 41, "n": 42, "|": 19, "[UNK]": 43, "[PAD]": 44}