训练后模型目录无文件

求助交流/
512
/
1
/
1年前

LX112}S($SMD90b3c9836b2cbe4dbe3a7e141b6fbce4a6a253ea4.png)
使用音频语音识别，识别无结果，日志如下
Microsoft Windows [版本 10.0.22631.3447]
(c) Microsoft Corporation。保留所有权利。D:\xiaowo\plugin\sovits_plugin\gpt>D:\xiaowo\lib\python-3.10.11\python start_sovits.py
0;管理员: C:\WINDOWS\system32\cmd.exe - D:\xiaowo\lib\python-3.10.11\python start_sovits.py
INFO: Started server process [2164]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:56567 (Press CTRL+C to quit)
INFO: 127.0.0.1:1965 - "GET / HTTP/1.1" 200 OK

tables: ----------- ** dataset_classes ** --------------
| class name | class location |
| AudioDataset | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\datasets\audio_datasets\datasets.py:7 |
----------- ** index_ds_classes ** --------------
| class name | class location |
| IndexDSJsonl | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\datasets\audio_datasets\index_ds.py:9 |
----------- ** batch_sampler_classes ** --------------
| class name | class location
|
| BatchSampler | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\datasets\audio_datasets\sampl
lers.py:7 |
----------- ** frontend_classes ** --------------
| class name | class location
|
| WavFrontend | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\frontends\wav_frontend.p
py:78 |
| WavFrontendOnline | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\frontends\wav_frontend.p
py:216 |
----------- ** encoder_classes ** --------------
| class name | class location
|
| BranchformerEncoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\branchformer
\encoder.py:294 |
| ConformerChunkEncoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\bat\conformer
r_chunk_encoder.py:315 |
| ConformerEncoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\conformer\enc
coder.py:286 |
| DFSMN | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\fsmn_vad_stre
eaming\encoder.py:232 |
| EBranchformerEncoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\e_branchforme
er\encoder.py:177 |
| FSMN | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\fsmn_vad_stre
eaming\encoder.py:161 |
| SANMEncoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\sanm\encoder.
.py:161 |
| SANMEncoderChunkOpt | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\scama\encoder
r.py:162 |
| SANMVadEncoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\ct_transforme
er_streaming\encoder.py:148 |
| TransformerEnc
oder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\transformer\e
encoder.py:139 |
----------- ** predictor_classes ** --------------
| class name | class location
|
| CifPredictor | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\paraformer\cif_predi
ictor.py:15 |
| CifPredictorV2 | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\paraformer\cif_predi
ictor.py:141 |
| CifPredictorV3 | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\bicif_paraformer\cif
f_predictor.py:95 |
----------- ** model_classes ** --------------
| class name | class location
|
| BiCifParaformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\bicif_parafo
ormer\model.py:37 |
| Branchformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\branchformer
r\model.py:6 |
| CAMPPlus | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\campplus\mod
del.py:30 |
| CTTransformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\ct_transform
mer\model.py:30 |
| CTTransformerStreaming | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\ct_transform
mer_streaming\model.py:27 |
| Conformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\conformer\mo
odel.py:8 |
| ContextualParaformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\contextual_p
paraformer\model.py:43 |
| EBranchformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\e_branchform
mer\model.py:6 |
| Emotion2vec
| D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\emotion2vec
\model.py:34 |
| FsmnVADStreaming | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\fsmn_vad_str
reaming\model.py:267 |
| MonotonicAligner | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\monotonic_al
ligner\model.py:24 |
| Paraformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\paraformer\m
model.py:26 |
| ParaformerStreaming | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\paraformer_s
streaming\model.py:37 |
| SANM | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\sanm\model.p
py:13 |
| SCAMA | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\scama\model.
.py:38 |
| SeacoParaformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\seaco_parafo
ormer\model.py:45 |
| Transformer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\transformer
\model.py:20 |
| UniASR | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\uniasr\model
l.py:26 |
----------- ** decoder_classes ** --------------
| class name | class location
|
| ContextualParaformerDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\contextual_paraformer\decoder.py:103 |
| DynamicConvolution2DTransformerDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\transformer\decoder.py:588 |
| DynamicConvolutionTransformerDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\transformer\decod
er.py:527 |
| FsmnDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\sanm\decoder.py:198 |
| FsmnDecoderSCAMAOpt | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\scama\decoder.py:197 |
| LightweightConvolution2DTransformerDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\transformer\decoder.py:465 |
| LightweightConvolutionTransformerDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\transformer\decoder.py:404 |
| ParaformerSANDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\paraformer\decoder.py:529 |
| ParaformerSANMDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\paraformer\decoder.py:204 |
| TransformerDecoder | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr
r\models\transformer\decoder.py:355 |
----------- ** normalize_classes ** --------------
| class name | class location
|
| GlobalMVN | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\normalize\global_mvn.p
py:11 |
| UtteranceMVN | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\normalize\utterance_mv
vn.py:8 |
----------- ** specaug_classes ** --------------
| class name | class location |
| SpecAug | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\specaug\specaug.py:14 |
| SpecAugLFR | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\models\specaug\specaug.py:104 |
----------- ** tokenizer_classes ** --------------
| class name | class location

|
| CharTokenizer | D:\xiaowo\lib\python-3.10.11\lib\site-packages\funasr\tokenizer\char_tokenizer.py:
:10 |
2024-04-26 16:27:45,296 - modelscope - INFO - PyTorch version 2.1.1+cu118 Found.
2024-04-26 16:27:45,298 - modelscope - INFO - Loading ast index from C:\Users\Administrator.cache\m
modelscope\ast_indexer
2024-04-26 16:27:45,404 - modelscope - INFO - Updating the files for the changes of local files, fir
rst time updating will take longer time! Please wait till updating done!
2024-04-26 16:27:45,414 - modelscope - INFO - AST-Scanning the path "D:\xiaowo\lib\python-3.10.11\Li
ib\site-packages\modelscope" with the following sub folders ['models', 'metrics', 'pipelines', 'prepr
rocessors', 'trainers', 'msdatasets', 'exporters']
2024-04-26 16:27:56,792 - modelscope - INFO - Scanning done! A number of 946 components indexed or u
updated! Time consumed 11.37786078453064s
2024-04-26 16:27:56,902 - modelscope - INFO - Loading done! Current index file version is 1.10.0, wi
ith md5 df1ca8e7bf144ae55de7e5b7beae1a91 and a total number of 946 components indexed
2024-04-26 16:27:57,341 - modelscope - INFO - Use user-specified model revision: v2.0.4
2024-04-26 16:27:59,774 - modelscope - INFO - Use user-specified model revision: v2.0.4
2024-04-26 16:28:00,262 - modelscope - INFO - Use user-specified model revision: v2.0.4
0it [00:00, ?it/s]
ASR 任务完成->标注文件路径: D:\xiaowo\plugin\sovits_plugin\gpt\output\asr_opt\1.list
INFO: 127.0.0.1:1966 - "POST / HTTP/1.1" 200 OK

赞同(0)
关注(1)
收藏(0)
1个回答默认排序 投票数排序
再见旧时光
再见旧时光
QQ：986004469 Email：986004469@qq.com
1年前

上面并没有开始训练，上面只是简单预处理数据，处理完毕后，选择已有模型进行训练

赞同(0)
收藏(0)
共 1 条
  • 1
前往
页
请先登录
0
1
0
1
https://upload.xiaowoai.com/static/images/avatar.png
while
这家伙很懒，什么也没写~
提问
1
回答
0
加入时间
1年前