bond005/whisper-large-v2-ru-podlodka
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: bond005/whisper-large-v2-ru-podlodka
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-16 05:51:14 +08:00
commit 7dc29ac00d
21 changed files with 156491 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

62
README.md Normal file
View File

@@ -0,0 +1,62 @@
---
license: apache-2.0
widget:
- example_title: Нейронные сети - это хорошо!
src: >-
https://huggingface.co/bond005/whisper-large-v2-ru-podlodka/resolve/main/test_sound_ru.flac
- example_title: >-
К сожалению, система распознавания речи не всегда стабильна, особенно в
шумных условиях.
src: >-
https://huggingface.co/bond005/whisper-large-v2-ru-podlodka/resolve/main/test_sound_with_noise.wav
- example_title: >-
Мимо театра мальчик ходил довольно часто — белое, со взбитыми сливками,
здание-торт.
src: >-
https://huggingface.co/bond005/whisper-large-v2-ru-podlodka/resolve/main/anna_matveeva_test.wav
datasets:
- bond005/taiga_speech_v2
- bond005/podlodka_speech
- bond005/rulibrispeech
language:
- ru
pipeline_tag: automatic-speech-recognition
metrics:
- wer
model-index:
- name: Whisper Large V2 Russian Podlodka by Ivan Bondarenko
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Podlodka.io
type: bond005/podlodka_speech
args: ru
metrics:
- name: WER (with punctuation and capital letters)
type: wer
value: 17.4103
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Podlodka.io
type: bond005/podlodka_speech
args: ru
metrics:
- name: WER (without punctuation)
type: wer
value: 9.0987
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Russian Librispeech
type: bond005/rulibrispeech
args: ru
metrics:
- name: WER (without punctuation)
type: wer
value: 20.961
---

108
added_tokens.json Normal file
View File

@@ -0,0 +1,108 @@
{
"<|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,
"<|nocaptions|>": 50362,
"<|notimestamps|>": 50363,
"<|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,
"<|startoflm|>": 50360,
"<|startofprev|>": 50361,
"<|startoftranscript|>": 50258,
"<|su|>": 50357,
"<|sv|>": 50273,
"<|sw|>": 50318,
"<|ta|>": 50287,
"<|te|>": 50299,
"<|tg|>": 50331,
"<|th|>": 50289,
"<|tk|>": 50341,
"<|tl|>": 50348,
"<|transcribe|>": 50359,
"<|translate|>": 50358,
"<|tr|>": 50268,
"<|tt|>": 50351,
"<|uk|>": 50280,
"<|ur|>": 50290,
"<|uz|>": 50337,
"<|vi|>": 50278,
"<|yi|>": 50335,
"<|yo|>": 50325,
"<|zh|>": 50260
}

BIN
anna_matveeva_test.wav Normal file
View File

Binary file not shown.

154
config.json Normal file
View File

@@ -0,0 +1,154 @@
{
"_name_or_path": "/storage0/bi/models/whisper-large-v2-ru",
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": false,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": [
220,
50257
],
"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": [
[
1,
50259
],
[
2,
50359
],
[
3,
50363
]
],
"init_std": 0.02,
"is_encoder_decoder": true,
"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,
"max_length": 448,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 80,
"pad_token_id": 50257,
"scale_embedding": false,
"suppress_tokens": [
1,
2,
7,
8,
9,
10,
14,
25,
26,
27,
28,
29,
31,
58,
59,
60,
61,
62,
63,
90,
91,
92,
93,
359,
503,
522,
542,
873,
893,
902,
918,
922,
931,
1350,
1853,
1982,
2460,
2627,
3246,
3253,
3268,
3536,
3846,
3961,
4183,
4667,
6585,
6647,
7273,
9061,
9383,
10428,
10929,
11938,
12033,
12331,
12562,
13793,
14157,
14635,
15265,
15618,
16553,
16604,
18362,
18956,
20075,
21675,
22520,
26130,
26161,
26435,
28279,
29464,
31650,
32302,
32470,
36865,
42863,
47425,
49870,
50254,
50258,
50358,
50359,
50360,
50361,
50362
],
"torch_dtype": "float32",
"transformers_version": "4.36.0",
"use_cache": true,
"use_weighted_layer_sum": false,
"vocab_size": 51865
}

319
generation_config.json Normal file
View File

@@ -0,0 +1,319 @@
{
"alignment_heads": [
[
10,
12
],
[
13,
17
],
[
16,
11
],
[
16,
12
],
[
16,
13
],
[
17,
15
],
[
17,
16
],
[
18,
4
],
[
18,
11
],
[
18,
19
],
[
19,
11
],
[
21,
2
],
[
21,
3
],
[
22,
3
],
[
22,
9
],
[
22,
12
],
[
23,
5
],
[
23,
7
],
[
23,
13
],
[
25,
5
],
[
26,
1
],
[
26,
12
],
[
27,
15
]
],
"begin_suppress_tokens": [
220,
50257
],
"bos_token_id": 50257,
"decoder_start_token_id": 50258,
"eos_token_id": 50257,
"forced_decoder_ids": [
[
1,
50263
],
[
2,
50359
],
[
3,
50363
]
],
"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,
"<|zh|>": 50260
},
"max_initial_timestamp_index": 1,
"max_length": 448,
"no_timestamps_token_id": 50363,
"pad_token_id": 50257,
"return_timestamps": false,
"suppress_tokens": [
1,
2,
7,
8,
9,
10,
14,
25,
26,
27,
28,
29,
31,
58,
59,
60,
61,
62,
63,
90,
91,
92,
93,
359,
503,
522,
542,
873,
893,
902,
918,
922,
931,
1350,
1853,
1982,
2460,
2627,
3246,
3253,
3268,
3536,
3846,
3961,
4183,
4667,
6585,
6647,
7273,
9061,
9383,
10428,
10929,
11938,
12033,
12331,
12562,
13793,
14157,
14635,
15265,
15618,
16553,
16604,
18362,
18956,
20075,
21675,
22520,
26130,
26161,
26435,
28279,
29464,
31650,
32302,
32470,
36865,
42863,
47425,
49870,
50254,
50258,
50358,
50359,
50360,
50361,
50362
],
"task_to_id": {
"transcribe": 50359,
"translate": 50358
},
"transformers_version": "4.36.0"
}

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46394b5637da010e8432dc6d219608d0aaeea6d4ab8da2a1dc99b8bd1ab5e84c
size 4992706480

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:415b59721576ece83c1f2297ccfb335a3c0761899abe469a65635a3f8efd9c89
size 1180663192

1266
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

1742
normalizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

14
preprocessor_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"chunk_length": 30,
"feature_extractor_type": "WhisperFeatureExtractor",
"feature_size": 80,
"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
pytorch_model-00001-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fe5da5af40208a572ed3d5e766850843f2766f56bc64d3ca72af6036daf38b8
size 4992929242

3
pytorch_model-00002-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44eeb6f685d15d23b553ab77d8f1dbe3006fa6568005210f1450b77472ddf1e6
size 1180723637

1267
pytorch_model.bin.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

133
special_tokens_map.json Normal file
View File

@@ -0,0 +1,133 @@
{
"additional_special_tokens": [
"<|endoftext|>",
"<|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|>",
"<|translate|>",
"<|transcribe|>",
"<|startoflm|>",
"<|startofprev|>",
"<|nocaptions|>",
"<|notimestamps|>"
],
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

BIN
test_sound_ru.flac Normal file
View File

Binary file not shown.

BIN
test_sound_with_noise.wav Normal file
View File

Binary file not shown.

101342
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"pad_token": null,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"special_tokens_map_file": null,
"tokenizer_class": "WhisperTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long