Merge feature-branch into main

.gitignore

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

README.md

@@ -11,7 +11,6 @@ should probably proofread and complete it, then remove this comment. -->
 
 # uaspeech-foundation-fintuned
 
-It achieves the following results on the evaluation set:
 - Loss: 2.5324
 - Wer: 1.2855
 

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "yongjian/wav2vec2-large-a",
+  "activation_dropout": 0.1,
+  "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": true,
+  "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": 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": "gelu",
+  "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": 0.1,
+  "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,
+  "model_type": "wav2vec2",
+  "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": 28,
+  "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": "4.23.1",
+  "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 sha256:3a055cddc071655a160dc6b709a1977abf8361ceeec541cf426dd832b63c98cf
+size 1262029937

runs/Nov21_06-37-38_6696bcd44a2b/events.out.tfevents.1669021909.6696bcd44a2b.106.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5315c9ca1d48de5dfc596648177ab5cec6a2f0626479d5d45ee844dd481bdd8
+size 364

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 sha256:69ef2849dd93fa9fb2aea89abb0e8f7fccb88d3568d959037d7d1022e4b8cd77
+size 3375

vocab.json

@@ -0,0 +1,31 @@
+{
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "a": 19,
+  "b": 24,
+  "c": 15,
+  "d": 21,
+  "e": 8,
+  "f": 12,
+  "g": 6,
+  "h": 5,
+  "i": 25,
+  "j": 1,
+  "k": 9,
+  "l": 18,
+  "m": 17,
+  "n": 2,
+  "o": 7,
+  "p": 11,
+  "q": 0,
+  "r": 14,
+  "s": 10,
+  "t": 4,
+  "u": 22,
+  "v": 20,
+  "w": 16,
+  "x": 26,
+  "y": 23,
+  "z": 3,
+  "|": 13
+}