first commit

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

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

README.md

@@ -0,0 +1,98 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: uaspeech-foundation-fintuned
+  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. -->
+
+# uaspeech-foundation-fintuned
+
+This model is a fine-tuned version of [yongjian/wav2vec2-large-a](https://huggingface.co/yongjian/wav2vec2-large-a) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5324
+- Wer: 1.2855
+
+## 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: 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
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 41.2984       | 0.7   | 500   | 2.8954          | 1.0    |
+| 3.0227        | 1.4   | 1000  | 2.8232          | 1.0042 |
+| 2.8283        | 2.11  | 1500  | 2.6291          | 1.0309 |
+| 2.5552        | 2.81  | 2000  | 2.2593          | 1.9170 |
+| 2.1714        | 3.51  | 2500  | 1.9586          | 1.9142 |
+| 1.8537        | 4.21  | 3000  | 1.5725          | 1.8579 |
+| 1.6087        | 4.92  | 3500  | 1.2772          | 1.7426 |
+| 1.3108        | 5.62  | 4000  | 1.2792          | 1.6751 |
+| 1.1652        | 6.32  | 4500  | 1.4565          | 1.6174 |
+| 1.0113        | 7.02  | 5000  | 1.1906          | 1.5626 |
+| 0.925         | 7.72  | 5500  | 1.4491          | 1.5260 |
+| 0.8183        | 8.43  | 6000  | 1.3712          | 1.5387 |
+| 0.7118        | 9.13  | 6500  | 1.4713          | 1.4866 |
+| 0.6959        | 9.83  | 7000  | 1.3336          | 1.4318 |
+| 0.6146        | 10.53 | 7500  | 1.3690          | 1.4177 |
+| 0.5655        | 11.24 | 8000  | 1.3789          | 1.4135 |
+| 0.4969        | 11.94 | 8500  | 1.5476          | 1.3966 |
+| 0.4705        | 12.64 | 9000  | 1.9062          | 1.3797 |
+| 0.4387        | 13.34 | 9500  | 1.2711          | 1.3924 |
+| 0.4115        | 14.04 | 10000 | 1.6318          | 1.3769 |
+| 0.3695        | 14.75 | 10500 | 1.5119          | 1.3755 |
+| 0.377         | 15.45 | 11000 | 1.6637          | 1.3812 |
+| 0.3788        | 16.15 | 11500 | 1.6636          | 1.3699 |
+| 0.3396        | 16.85 | 12000 | 1.6572          | 1.3418 |
+| 0.3047        | 17.56 | 12500 | 1.4740          | 1.3361 |
+| 0.2804        | 18.26 | 13000 | 2.0885          | 1.3249 |
+| 0.2995        | 18.96 | 13500 | 1.9536          | 1.3235 |
+| 0.2628        | 19.66 | 14000 | 1.7736          | 1.3179 |
+| 0.2703        | 20.37 | 14500 | 2.0018          | 1.3291 |
+| 0.2335        | 21.07 | 15000 | 1.7962          | 1.3221 |
+| 0.2068        | 21.77 | 15500 | 2.3187          | 1.3136 |
+| 0.2311        | 22.47 | 16000 | 2.4853          | 1.3291 |
+| 0.2491        | 23.17 | 16500 | 2.1901          | 1.3024 |
+| 0.1836        | 23.88 | 17000 | 2.4344          | 1.2911 |
+| 0.1823        | 24.58 | 17500 | 2.3705          | 1.3066 |
+| 0.1575        | 25.28 | 18000 | 2.1864          | 1.2897 |
+| 0.1451        | 25.98 | 18500 | 2.4216          | 1.2883 |
+| 0.1502        | 26.69 | 19000 | 2.1780          | 1.2855 |
+| 0.1392        | 27.39 | 19500 | 2.4009          | 1.2925 |
+| 0.1609        | 28.09 | 20000 | 2.4250          | 1.2982 |
+| 0.1066        | 28.79 | 20500 | 2.4433          | 1.2897 |
+| 0.1514        | 29.49 | 21000 | 2.5063          | 1.2855 |
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- Pytorch 1.12.1+cu113
+- Datasets 1.18.3
+- Tokenizers 0.13.2

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
+}