initial commit

config.json

@@ -0,0 +1,114 @@
+{
+  "_name_or_path": "facebook/wav2vec2-conformer-rope-large-960h-ft",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ConformerForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_depthwise_kernel_size": 31,
+  "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": "sum",
+  "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": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 0.05,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-conformer",
+  "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,
+  "position_embeddings_type": "rotary",
+  "proj_codevector_dim": 768,
+  "rotary_embedding_base": 10000,
+  "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": "4.20.1",
+  "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 sha256:580594ee9975f1c251b2470cd3d6e0193765b714cccdf25f97f6419bf6eef333
+size 2374006415

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d16b5f9a88e3a9364cee3741aa6358951112bdc4da47d076a86bd0b9536279f
+size 3439

training_args_tracker.txt

@@ -0,0 +1,25 @@
+from transformers import TrainingArguments
+
+steps = 200
+
+training_args = TrainingArguments(
+  output_dir=outmodelpath,
+  overwrite_output_dir=True, #Set to true to overwrite output directory
+  group_by_length=True, # group data with same length to save memory (only for dynamic padding)
+  per_device_train_batch_size=8, #16
+  #save_strategy="steps",# The checkpoint save strategy to adopt during training.
+  evaluation_strategy="steps", # alternative: None, epoch
+  num_train_epochs=5, #50
+  #max_gradient_norm=0.8, #Maximum gradient norm (for gradient clipping). Default: 1.0
+  fp16=True, # Available only on GPU, when set true save memory
+  gradient_checkpointing=True, # save memory at the expense of slower backward pass
+  save_steps=steps, 
+  eval_steps=steps,
+  logging_steps=steps,
+  learning_rate=1e-4, # default: 5e-5
+  weight_decay=0.005, # prevent overfitting, generalize better
+  warmup_ratio=0.1, # Ratio of total training steps used for a linear warmup from 0 to learning_rate. default 0.0
+  max_grad_norm=0.8,  
+  save_total_limit=2, # number of checkpoint to save
+  load_best_model_at_end=True #load best model to save the best model in trainer.save_model
+)

vocab.json

@@ -0,0 +1,32 @@
+{
+  "'": 7,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "a": 20,
+  "b": 22,
+  "c": 18,
+  "d": 21,
+  "e": 3,
+  "f": 17,
+  "g": 5,
+  "h": 2,
+  "i": 25,
+  "j": 1,
+  "k": 0,
+  "l": 12,
+  "m": 9,
+  "n": 8,
+  "o": 26,
+  "p": 13,
+  "q": 16,
+  "r": 14,
+  "s": 11,
+  "t": 6,
+  "u": 27,
+  "v": 10,
+  "w": 15,
+  "x": 19,
+  "y": 4,
+  "z": 24,
+  "|": 23
+}