KasuleTrevor/cdli-whisper-ml-eng-lug-full-a40-5e-5
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: KasuleTrevor/cdli-whisper-ml-eng-lug-full-a40-5e-5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 01:04:12 +08:00
commit 6076bb9561
35 changed files with 238670 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1611
last-checkpoint/added_tokens.json Normal file
View File

File diff suppressed because it is too large Load Diff

47
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,47 @@
{
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": true,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": null,
"bos_token_id": 50257,
"classifier_proj_size": 256,
"d_model": 1280,
"decoder_attention_heads": 20,
"decoder_ffn_dim": 5120,
"decoder_layerdrop": 0.0,
"decoder_layers": 32,
"decoder_start_token_id": 50258,
"dropout": 0.0,
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"eos_token_id": 50257,
"forced_decoder_ids": null,
"init_std": 0.02,
"is_encoder_decoder": true,
"mask_feature_length": 10,
"mask_feature_min_masks": 2,
"mask_feature_prob": 0.05,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"max_length": null,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 128,
"pad_token_id": 50256,
"scale_embedding": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.0",
"use_cache": false,
"use_weighted_layer_sum": false,
"vocab_size": 51866
}

168
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,168 @@
{
"alignment_heads": [
[
7,
0
],
[
10,
17
],
[
12,
18
],
[
13,
12
],
[
16,
1
],
[
17,
14
],
[
19,
11
],
[
21,
4
],
[
24,
1
],
[
25,
6
]
],
"begin_suppress_tokens": [
220,
50257
],
"bos_token_id": 50257,
"decoder_start_token_id": 50258,
"eos_token_id": 50257,
"is_multilingual": true,
"lang_to_id": {
"<|af|>": 50327,
"<|am|>": 50334,
"<|ar|>": 50272,
"<|as|>": 50350,
"<|az|>": 50304,
"<|ba|>": 50355,
"<|be|>": 50330,
"<|bg|>": 50292,
"<|bn|>": 50302,
"<|bo|>": 50347,
"<|br|>": 50309,
"<|bs|>": 50315,
"<|ca|>": 50270,
"<|cs|>": 50283,
"<|cy|>": 50297,
"<|da|>": 50285,
"<|de|>": 50261,
"<|el|>": 50281,
"<|en|>": 50259,
"<|es|>": 50262,
"<|et|>": 50307,
"<|eu|>": 50310,
"<|fa|>": 50300,
"<|fi|>": 50277,
"<|fo|>": 50338,
"<|fr|>": 50265,
"<|gl|>": 50319,
"<|gu|>": 50333,
"<|haw|>": 50352,
"<|ha|>": 50354,
"<|he|>": 50279,
"<|hi|>": 50276,
"<|hr|>": 50291,
"<|ht|>": 50339,
"<|hu|>": 50286,
"<|hy|>": 50312,
"<|id|>": 50275,
"<|is|>": 50311,
"<|it|>": 50274,
"<|ja|>": 50266,
"<|jw|>": 50356,
"<|ka|>": 50329,
"<|kk|>": 50316,
"<|km|>": 50323,
"<|kn|>": 50306,
"<|ko|>": 50264,
"<|la|>": 50294,
"<|lb|>": 50345,
"<|ln|>": 50353,
"<|lo|>": 50336,
"<|lt|>": 50293,
"<|lv|>": 50301,
"<|mg|>": 50349,
"<|mi|>": 50295,
"<|mk|>": 50308,
"<|ml|>": 50296,
"<|mn|>": 50314,
"<|mr|>": 50320,
"<|ms|>": 50282,
"<|mt|>": 50343,
"<|my|>": 50346,
"<|ne|>": 50313,
"<|nl|>": 50271,
"<|nn|>": 50342,
"<|no|>": 50288,
"<|oc|>": 50328,
"<|pa|>": 50321,
"<|pl|>": 50269,
"<|ps|>": 50340,
"<|pt|>": 50267,
"<|ro|>": 50284,
"<|ru|>": 50263,
"<|sa|>": 50344,
"<|sd|>": 50332,
"<|si|>": 50322,
"<|sk|>": 50298,
"<|sl|>": 50305,
"<|sn|>": 50324,
"<|so|>": 50326,
"<|sq|>": 50317,
"<|sr|>": 50303,
"<|su|>": 50357,
"<|sv|>": 50273,
"<|sw|>": 50318,
"<|ta|>": 50287,
"<|te|>": 50299,
"<|tg|>": 50331,
"<|th|>": 50289,
"<|tk|>": 50341,
"<|tl|>": 50348,
"<|tr|>": 50268,
"<|tt|>": 50351,
"<|uk|>": 50280,
"<|ur|>": 50290,
"<|uz|>": 50337,
"<|vi|>": 50278,
"<|yi|>": 50335,
"<|yo|>": 50325,
"<|yue|>": 50358,
"<|zh|>": 50260
},
"language": null,
"max_initial_timestamp_index": 50,
"max_length": 448,
"no_timestamps_token_id": 50364,
"pad_token_id": 50257,
"prev_sot_token_id": 50362,
"return_timestamps": false,
"suppress_tokens": [],
"task": "transcribe",
"task_to_id": {
"transcribe": 50360,
"translate": 50359
},
"transformers_version": "4.52.0"
}

50001
last-checkpoint/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
last-checkpoint/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d86b51a28ec1c55503d1ccc559b47d4c73f9028dc82540618c1f7fa947097120
size 3087132232

1742
last-checkpoint/normalizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
last-checkpoint/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24630d6bdf5f12f6f5567dff03a1da5ae29b38fb50e030f0aa9e8476cba53b98
size 6175072292

15
last-checkpoint/preprocessor_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"chunk_length": 30,
"dither": 0.0,
"feature_extractor_type": "WhisperFeatureExtractor",
"feature_size": 128,
"hop_length": 160,
"n_fft": 400,
"n_samples": 480000,
"nb_max_frames": 3000,
"padding_side": "right",
"padding_value": 0.0,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"sampling_rate": 16000
}

3
last-checkpoint/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f020f2c25dd3371d3f47f373cf66bcee3219d79c64bdfa46d46cf8f4fa92d182
size 14709

3
last-checkpoint/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a055373b6616927821990112c9bcc54deefdc796454a5ecd2e7b2953f9568926
size 1465

139
last-checkpoint/special_tokens_map.json Normal file
View File

@@ -0,0 +1,139 @@
{
"additional_special_tokens": [
"<|startoftranscript|>",
"<|en|>",
"<|zh|>",
"<|de|>",
"<|es|>",
"<|ru|>",
"<|ko|>",
"<|fr|>",
"<|ja|>",
"<|pt|>",
"<|tr|>",
"<|pl|>",
"<|ca|>",
"<|nl|>",
"<|ar|>",
"<|sv|>",
"<|it|>",
"<|id|>",
"<|hi|>",
"<|fi|>",
"<|vi|>",
"<|he|>",
"<|uk|>",
"<|el|>",
"<|ms|>",
"<|cs|>",
"<|ro|>",
"<|da|>",
"<|hu|>",
"<|ta|>",
"<|no|>",
"<|th|>",
"<|ur|>",
"<|hr|>",
"<|bg|>",
"<|lt|>",
"<|la|>",
"<|mi|>",
"<|ml|>",
"<|cy|>",
"<|sk|>",
"<|te|>",
"<|fa|>",
"<|lv|>",
"<|bn|>",
"<|sr|>",
"<|az|>",
"<|sl|>",
"<|kn|>",
"<|et|>",
"<|mk|>",
"<|br|>",
"<|eu|>",
"<|is|>",
"<|hy|>",
"<|ne|>",
"<|mn|>",
"<|bs|>",
"<|kk|>",
"<|sq|>",
"<|sw|>",
"<|gl|>",
"<|mr|>",
"<|pa|>",
"<|si|>",
"<|km|>",
"<|sn|>",
"<|yo|>",
"<|so|>",
"<|af|>",
"<|oc|>",
"<|ka|>",
"<|be|>",
"<|tg|>",
"<|sd|>",
"<|gu|>",
"<|am|>",
"<|yi|>",
"<|lo|>",
"<|uz|>",
"<|fo|>",
"<|ht|>",
"<|ps|>",
"<|tk|>",
"<|nn|>",
"<|mt|>",
"<|sa|>",
"<|lb|>",
"<|my|>",
"<|bo|>",
"<|tl|>",
"<|mg|>",
"<|as|>",
"<|tt|>",
"<|haw|>",
"<|ln|>",
"<|ha|>",
"<|ba|>",
"<|jw|>",
"<|su|>",
"<|yue|>",
"<|translate|>",
"<|transcribe|>",
"<|startoflm|>",
"<|startofprev|>",
"<|nospeech|>",
"<|notimestamps|>"
],
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

12997
last-checkpoint/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

1314
last-checkpoint/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
last-checkpoint/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e9ae1e14cb5254830c9ba92acab84551412f3fc17a4b6d27f67573489c81cef9
size 6033

50259
last-checkpoint/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff