初始化项目，由ModelHub XC社区提供模型
Model: kresnik/wav2vec2-large-xls-r-300m-korean Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
*.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
|
||||
125
README.md
Normal file
125
README.md
Normal file
@@ -0,0 +1,125 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: facebook/wav2vec2-xls-r-300m
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- common_voice_13_0
|
||||
metrics:
|
||||
- wer
|
||||
model-index:
|
||||
- name: wav2vec2-large-xls-r-300m-korean
|
||||
results:
|
||||
- task:
|
||||
name: Automatic Speech Recognition
|
||||
type: automatic-speech-recognition
|
||||
dataset:
|
||||
name: common_voice_13_0
|
||||
type: common_voice_13_0
|
||||
config: ko
|
||||
split: test
|
||||
args: ko
|
||||
metrics:
|
||||
- name: Wer
|
||||
type: wer
|
||||
value: 0.5931520644511581
|
||||
---
|
||||
|
||||
<!-- 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-large-xls-r-300m-korean
|
||||
|
||||
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 1.4687
|
||||
- Wer: 0.5932
|
||||
|
||||
## 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: 0.0003
|
||||
- train_batch_size: 16
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 32
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: linear
|
||||
- lr_scheduler_warmup_steps: 500
|
||||
- num_epochs: 300
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
||||
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
||||
| 20.8922 | 6.25 | 400 | 4.6827 | 0.9990 |
|
||||
| 4.0513 | 12.5 | 800 | 2.3657 | 0.9204 |
|
||||
| 1.5386 | 18.75 | 1200 | 1.2355 | 0.7392 |
|
||||
| 0.7429 | 25.0 | 1600 | 1.1179 | 0.6636 |
|
||||
| 0.3746 | 31.25 | 2000 | 1.0465 | 0.6314 |
|
||||
| 0.2407 | 37.5 | 2400 | 1.1492 | 0.6596 |
|
||||
| 0.1966 | 43.75 | 2800 | 1.1291 | 0.6344 |
|
||||
| 0.1697 | 50.0 | 3200 | 1.1897 | 0.6395 |
|
||||
| 0.1533 | 56.25 | 3600 | 1.2202 | 0.6193 |
|
||||
| 0.129 | 62.5 | 4000 | 1.2106 | 0.6516 |
|
||||
| 0.1097 | 68.75 | 4400 | 1.1662 | 0.6254 |
|
||||
| 0.102 | 75.0 | 4800 | 1.2086 | 0.6133 |
|
||||
| 0.0918 | 81.25 | 5200 | 1.2295 | 0.6485 |
|
||||
| 0.0806 | 87.5 | 5600 | 1.2861 | 0.6123 |
|
||||
| 0.0738 | 93.75 | 6000 | 1.2436 | 0.6093 |
|
||||
| 0.0697 | 100.0 | 6400 | 1.3496 | 0.6626 |
|
||||
| 0.0667 | 106.25 | 6800 | 1.2364 | 0.6133 |
|
||||
| 0.0591 | 112.5 | 7200 | 1.2689 | 0.6062 |
|
||||
| 0.054 | 118.75 | 7600 | 1.2886 | 0.6183 |
|
||||
| 0.0523 | 125.0 | 8000 | 1.3328 | 0.6445 |
|
||||
| 0.0542 | 131.25 | 8400 | 1.4019 | 0.6133 |
|
||||
| 0.045 | 137.5 | 8800 | 1.3426 | 0.6042 |
|
||||
| 0.0425 | 143.75 | 9200 | 1.3042 | 0.6032 |
|
||||
| 0.0378 | 150.0 | 9600 | 1.3638 | 0.6224 |
|
||||
| 0.0354 | 156.25 | 10000 | 1.3397 | 0.6294 |
|
||||
| 0.0282 | 162.5 | 10400 | 1.3939 | 0.6173 |
|
||||
| 0.0288 | 168.75 | 10800 | 1.3674 | 0.6475 |
|
||||
| 0.0278 | 175.0 | 11200 | 1.3636 | 0.6324 |
|
||||
| 0.0239 | 181.25 | 11600 | 1.4101 | 0.6405 |
|
||||
| 0.0238 | 187.5 | 12000 | 1.4528 | 0.6163 |
|
||||
| 0.0214 | 193.75 | 12400 | 1.4458 | 0.6093 |
|
||||
| 0.0194 | 200.0 | 12800 | 1.3920 | 0.6304 |
|
||||
| 0.0168 | 206.25 | 13200 | 1.4277 | 0.6193 |
|
||||
| 0.0168 | 212.5 | 13600 | 1.3959 | 0.6203 |
|
||||
| 0.0154 | 218.75 | 14000 | 1.4043 | 0.6133 |
|
||||
| 0.0144 | 225.0 | 14400 | 1.4508 | 0.6193 |
|
||||
| 0.0134 | 231.25 | 14800 | 1.4309 | 0.6224 |
|
||||
| 0.0109 | 237.5 | 15200 | 1.4301 | 0.6123 |
|
||||
| 0.0107 | 243.75 | 15600 | 1.4373 | 0.6002 |
|
||||
| 0.0098 | 250.0 | 16000 | 1.4147 | 0.6113 |
|
||||
| 0.0095 | 256.25 | 16400 | 1.4585 | 0.6193 |
|
||||
| 0.009 | 262.5 | 16800 | 1.4424 | 0.6203 |
|
||||
| 0.0079 | 268.75 | 17200 | 1.5019 | 0.6193 |
|
||||
| 0.0066 | 275.0 | 17600 | 1.4835 | 0.5932 |
|
||||
| 0.0059 | 281.25 | 18000 | 1.4749 | 0.5992 |
|
||||
| 0.0057 | 287.5 | 18400 | 1.4897 | 0.6002 |
|
||||
| 0.0053 | 293.75 | 18800 | 1.4667 | 0.5901 |
|
||||
| 0.0048 | 300.0 | 19200 | 1.4687 | 0.5932 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.35.0.dev0
|
||||
- Pytorch 1.12.1
|
||||
- Datasets 2.14.5
|
||||
- Tokenizers 0.14.0
|
||||
6
added_tokens.json
Normal file
6
added_tokens.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"</s>": 1083,
|
||||
"<s>": 1082,
|
||||
"[PAD]": 1081,
|
||||
"[UNK]": 1080
|
||||
}
|
||||
109
config.json
Normal file
109
config.json
Normal file
@@ -0,0 +1,109 @@
|
||||
{
|
||||
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
||||
"activation_dropout": 0.0,
|
||||
"adapter_attn_dim": null,
|
||||
"adapter_kernel_size": 3,
|
||||
"adapter_stride": 2,
|
||||
"add_adapter": false,
|
||||
"apply_spec_augment": true,
|
||||
"architectures": [
|
||||
"Wav2Vec2ForCTC"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"classifier_proj_size": 256,
|
||||
"codevector_dim": 768,
|
||||
"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": 0.0,
|
||||
"feat_quantizer_dropout": 0.0,
|
||||
"final_dropout": 0.0,
|
||||
"gradient_checkpointing": false,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.0,
|
||||
"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,
|
||||
"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": 1081,
|
||||
"proj_codevector_dim": 768,
|
||||
"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": "4.35.0.dev0",
|
||||
"use_weighted_layer_sum": false,
|
||||
"vocab_size": 1084,
|
||||
"xvector_output_dim": 512
|
||||
}
|
||||
9
preprocessor_config.json
Normal file
9
preprocessor_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"do_normalize": true,
|
||||
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
||||
"feature_size": 1,
|
||||
"padding_side": "right",
|
||||
"padding_value": 0.0,
|
||||
"return_attention_mask": true,
|
||||
"sampling_rate": 16000
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45591b8cb3d9efe781c5f08f1e04c8158f622b3e272162fa391f9a65eab8da1a
|
||||
size 1266343089
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "[PAD]",
|
||||
"unk_token": "[UNK]"
|
||||
}
|
||||
49
tokenizer_config.json
Normal file
49
tokenizer_config.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"1080": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"1081": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"1082": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1083": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"do_lower_case": false,
|
||||
"eos_token": "</s>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "[PAD]",
|
||||
"replace_word_delimiter_char": " ",
|
||||
"target_lang": null,
|
||||
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
||||
"tokenizer_file": null,
|
||||
"unk_token": "[UNK]",
|
||||
"word_delimiter_token": "|"
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:567f05d6f16acaaa1274bec36fa2a7907ed109691ab37ee4c9c0c33e5f09fbb5
|
||||
size 4079
|
||||
1084
vocab.json
Normal file
1084
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user