ZikXewen/wav2vec2-large-xlsr-53-thai-demo
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ZikXewen/wav2vec2-large-xlsr-53-thai-demo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-28 11:03:18 +08:00
commit 9ed036ebaa
14 changed files with 270 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
.gitattributes vendored Normal file
View File

@@ -0,0 +1,17 @@
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tar.gz filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text

84
config.json Normal file
View File

@@ -0,0 +1,84 @@
{
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
"activation_dropout": 0.0,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"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": 0.1,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"gradient_checkpointing": true,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"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": 0.075,
"mask_time_selection": "static",
"model_type": "wav2vec2",
"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,
"pad_token_id": 70,
"proj_codevector_dim": 768,
"transformers_version": "4.8.1",
"vocab_size": 73
}

3
flax_model.msgpack Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f83b54c909bc937e4f30e171cfe18c2dd61ec7d0ee64faa509f1ff7b7debe8f
size 1262069574

3
optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:640d3248efc4749756152e3931ba16322af55bfa75cb93adde7b9671703a52f5
size 2490657553

9
preprocessor_config.json Normal file
View 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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:815ce4f48b732198a0e83879aa6353cb6f1954d96b8cdd209ee05cf74b50e066
size 1262222961

3
rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ea5972ee1e8528291bf676f424b25bfaec398b61d17dfd328bc984546980544
size 14631

3
scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c3de5c4545ae0615ca3f287f4fc8f8c5321fbeba6a51f4e4fce1f5d4155e19ed
size 559

3
scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13bca7a62c95be7bf889fe09343566183dba689324be024d7d0ed49b9d504ff9
size 623

1
special_tokens_map.json Normal file
View File

@@ -0,0 +1 @@
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}

136
trainer_state.json Normal file
View File

@@ -0,0 +1,136 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.59504132231405,
"global_step": 3200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.32,
"learning_rate": 0.000237,
"loss": 6.8607,
"step": 400
},
{
"epoch": 1.32,
"eval_cer": 0.9999129564346956,
"eval_loss": 3.4867048263549805,
"eval_runtime": 258.7779,
"eval_samples_per_second": 8.455,
"eval_steps_per_second": 1.059,
"step": 400
},
{
"epoch": 2.65,
"learning_rate": 0.0002840252707581227,
"loss": 2.7103,
"step": 800
},
{
"epoch": 2.65,
"eval_cer": 0.3108760934847891,
"eval_loss": 1.061523675918579,
"eval_runtime": 261.8355,
"eval_samples_per_second": 8.356,
"eval_steps_per_second": 1.046,
"step": 800
},
{
"epoch": 3.97,
"learning_rate": 0.0002623646209386281,
"loss": 1.0054,
"step": 1200
},
{
"epoch": 3.97,
"eval_cer": 0.22384703544123835,
"eval_loss": 0.6996724605560303,
"eval_runtime": 261.6376,
"eval_samples_per_second": 8.363,
"eval_steps_per_second": 1.047,
"step": 1200
},
{
"epoch": 5.3,
"learning_rate": 0.00024070397111913356,
"loss": 0.6836,
"step": 1600
},
{
"epoch": 5.3,
"eval_cer": 0.19226472849661255,
"eval_loss": 0.6144178509712219,
"eval_runtime": 259.8219,
"eval_samples_per_second": 8.421,
"eval_steps_per_second": 1.055,
"step": 1600
},
{
"epoch": 6.62,
"learning_rate": 0.00021904332129963898,
"loss": 0.5372,
"step": 2000
},
{
"epoch": 6.62,
"eval_cer": 0.1836474155314735,
"eval_loss": 0.60425865650177,
"eval_runtime": 259.9127,
"eval_samples_per_second": 8.418,
"eval_steps_per_second": 1.054,
"step": 2000
},
{
"epoch": 7.95,
"learning_rate": 0.0001973826714801444,
"loss": 0.4427,
"step": 2400
},
{
"epoch": 7.95,
"eval_cer": 0.16931424177800988,
"eval_loss": 0.5793657898902893,
"eval_runtime": 260.1302,
"eval_samples_per_second": 8.411,
"eval_steps_per_second": 1.053,
"step": 2400
},
{
"epoch": 9.27,
"learning_rate": 0.0001757220216606498,
"loss": 0.3773,
"step": 2800
},
{
"epoch": 9.27,
"eval_cer": 0.1633082357720039,
"eval_loss": 0.6081105470657349,
"eval_runtime": 260.6021,
"eval_samples_per_second": 8.396,
"eval_steps_per_second": 1.051,
"step": 2800
},
{
"epoch": 10.6,
"learning_rate": 0.0001540613718411552,
"loss": 0.3241,
"step": 3200
},
{
"epoch": 10.6,
"eval_cer": 0.15936226081153618,
"eval_loss": 0.6171871423721313,
"eval_runtime": 260.2528,
"eval_samples_per_second": 8.407,
"eval_steps_per_second": 1.053,
"step": 3200
}
],
"max_steps": 6040,
"num_train_epochs": 20,
"total_flos": 6.610023346999888e+18,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c029403bc722a36fa6eae21e60b868e397e2bf017148447664da681a437b0a56
size 2607

1
vocab.json Normal file
View File

@@ -0,0 +1 @@
{"ฑ": 0, "ญ": 1, "ล": 2, "ส": 3, "ซ": 4, "’": 5, "น": 6, "ช": 7, "ด": 8, "ภ": 9, "า": 10, "บ": 11, "ู": 12, "็": 13, "ี": 14, "ฤ": 15, "'": 16, "่": 17, "ม": 18, "ฝ": 19, "ป": 20, "ำ": 21, "ุ": 22, "ฎ": 23, "ไ": 24, "ฆ": 25, "๊": 27, "ฮ": 28, "์": 29, "ก": 30, "ฬ": 31, "ร": 32, "ย": 33, "ผ": 34, "ษ": 35, "ฐ": 36, "ั": 37, "ค": 38, "ิ": 39, "ะ": 40, "แ": 41, "้": 42, "ถ": 43, "เ": 44, "พ": 45, "อ": 46, "ฏ": 47, "ๆ": 48, "ง": 49, "ํ": 50, "ฟ": 51, "โ": 52, "ื": 53, "ข": 54, "๋": 55, "ๅ": 56, "ต": 57, "ณ": 58, "ฉ": 59, "ห": 60, "จ": 61, "ใ": 62, "ว": 63, "ศ": 64, "ท": 65, "ึ": 66, "ธ": 67, "ฒ": 68, "<unk>": 69, "<pad>": 70, "|": 26}