add tokenizer

README.md

@@ -1,53 +0,0 @@
----
-license: apache-2.0
-tags:
-- generated_from_trainer
-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.
-
-## 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: 1
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.11.3
-- Pytorch 1.9.0+cu111
-- Datasets 1.13.3
-- Tokenizers 0.10.3

config.json

@@ -1,88 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "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": 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,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
-  "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": "4.11.3",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32
-}

preprocessor_config.json

@@ -1,9 +0,0 @@
-{
-  "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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f52d328d4aa0e5b2d7196703de804783c8f277debc72d02e341e9fbdf67f43b2
-size 377670039

runs/Nov01_02-01-41_87f138463f89/1635732190.821911/events.out.tfevents.1635732190.87f138463f89.79.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f8751f90fbe2abce80a47ee5ff650b8071c114d660432f8e91d401160cf942a
-size 4555

runs/Nov01_02-01-41_87f138463f89/events.out.tfevents.1635732190.87f138463f89.79.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1708bba7b59a500a3448ebba81ddb8c53a45f210070a7a6e467431f5ea6e3db
-size 4812

runs/Nov01_02-50-35_87f138463f89/1635735133.780516/events.out.tfevents.1635735133.87f138463f89.79.3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:73d7a1fb05c630ac11c7252aefa384d0701c6ce35f3e93218111c3de2a06b0ef
-size 4555

runs/Nov01_02-50-35_87f138463f89/events.out.tfevents.1635735133.87f138463f89.79.2

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f93c21da93e85438fc5155c3f44b33d00281a78567eaf2200c07421f7980ba3
-size 4211

runs/Oct29_00-56-06_4b2d81d172ac/1635469130.8362846/events.out.tfevents.1635469130.4b2d81d172ac.77.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d9de4fac2d1b9721bbfd6dfe3add2ea9a44f7f51ab6d00733a7fb30b11f9fea2
-size 4555

runs/Oct29_00-56-06_4b2d81d172ac/events.out.tfevents.1635469130.4b2d81d172ac.77.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5dbfe73f0df650940c6e456da49b68f6180b8e3416116a55130973a1b718370c
-size 4622

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:088e9ffd4004d3aab2a23a82fb74cee8472b507cb960365b3b53fd7674058693
-size 2863