add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- null
+model_index:
+- name: wav2vec2-base-timit-demo-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-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: 0.4634
+- Wer: 0.3469
+
+## 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
+- 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    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.4469        | 4.0   | 500  | 1.2851          | 0.9547 |
+| 0.616         | 8.0   | 1000 | 0.4867          | 0.4572 |
+| 0.2324        | 12.0  | 1500 | 0.4432          | 0.3814 |
+| 0.1338        | 16.0  | 2000 | 0.4169          | 0.3685 |
+| 0.0893        | 20.0  | 2500 | 0.4634          | 0.3632 |
+| 0.0631        | 24.0  | 3000 | 0.4804          | 0.3541 |
+| 0.0497        | 28.0  | 3500 | 0.4634          | 0.3469 |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.17.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,87 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "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,
+  "gradient_checkpointing": 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_prob": 0.0,
+  "mask_time_length": 10,
+  "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_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,
+  "pad_token_id": 29,
+  "proj_codevector_dim": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "vocab_size": 32
+}

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 sha256:1b2fcf8a34b2fa94c6d539d796740544265edc82f62dc78e9709554e9b49afaf
+size 377670039

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3525ce693ff1a560cef03e05cced987bc53418307793029bef8d9b71b29cf858
+size 2607