LauraGPT
a57cc3f92a
fix(sensevoice): keep words separate at standalone boundaries
...
Signed-off-by: LauraGPT <[email protected]
2026-09-29 06:12:59 +00:00
LauraGPT
2ddabb2c91
fix(sensevoice): normalize first word before joining subpieces
...
Signed-off-by: LauraGPT <[email protected]
2026-09-29 05:58:08 +00:00
谢翊凡
9413d7d768
fix: use torch.amp via compatibility shim ( #3518 )
...
Use the non-deprecated torch.amp APIs when available while preserving the torch.cuda.amp fallback and legacy autocast argument semantics on older PyTorch releases.
2026-08-26 20:10:53 +08:00
liuweiqing
57e2f48c2c
fix(tokenizer): treat special-token strings as text to prevent batch crashes ( #3110 )
...
Fixes #3110 .
2026-07-07 14:42:36 +08:00
zhifu gao
e79afd551b
fix(sense_voice): remove docstring between @triton.jit and def (SyntaxError) ( #3027 )
2026-06-23 16:09:27 +08:00
游雁
78cc132a51
docs: add docstrings to 1950 functions across 276 files for API documentation
2026-05-21 07:52:52 +00:00
游雁
bff79be1a2
fix: add super().__init__() to SinusoidalPositionEncoder classes; add VAD streaming test
...
- Fix SinusoidalPositionEncoder and StreamSinusoidalPositionEncoder in transformer/embedding.py
- Fix SinusoidalPositionEncoder in sense_voice/model.py
- Missing super().__init__() caused state_dict() crash with newer PyTorch versions
- Add test_fsmn_vad_streaming.py: chunk-by-chunk VAD test with consistency check
2026-05-19 16:46:37 +00:00
游雁
22bb089e3a
fix: correct __int__ typo to __init__ in SinusoidalPositionEncoder
...
Three classes had __int__ instead of __init__, causing the constructor
to never be called. Affected files:
- funasr/models/sense_voice/model.py (SinusoidalPositionEncoder)
- funasr/models/transformer/embedding.py (SinusoidalPositionEncoder)
- funasr/models/transformer/embedding.py (StreamSinusoidalPositionEncoder)
2026-05-19 15:06:25 +00:00
游雁
a2f3d5483d
fix: resolve multiple issues ( #2689 , #2720 , #2755 , #2780 )
...
- #2689 : Add text_language check before removing spaces for aishell data
- #2720 : Fix streaming ASR code example syntax error in README
- #2755 : Use log_softmax instead of softmax for CTC forced alignment in SenseVoice
- #2780 : Add bounds check in GetFrameState to prevent IndexError with non-default decibel_thres
2026-05-19 14:14:10 +00:00
彭震东 and 启焚
1bf72e7ff8
add whisper_lib for sensevoice ( #2735 )
...
Co-authored-by: 启焚 <[email protected]
2025-12-09 17:08:08 +08:00
slin000111
88b464edb9
Fix prefix concatenation in timestamp post-processing for sensevoice ( #2670 )
...
* fix prefix concatenation in timestamp post-processing for sensevoice
* Remove unnecessary code
2025-09-20 22:40:30 +08:00
chengligen
8b0fb74bde
feat: add 'words' key aligned with timestamps in sensevoice model output ( #2531 )
2025-05-26 14:11:33 +08:00
Isuxiz Slidder
3df109adfc
Update model.py to fix "IndexError: index 1 is out of bounds for dimension 1 with size 0" ( #2454 )
...
* Update model.py
Avoid exception of "IndexError: index 1 is out of bounds for dimension 1 with size 0"
* Update model.py
Add return word in timestamps
* Revert "Update model.py"
This reverts commit bc736df302
2025-03-31 17:51:52 +08:00
passerbya
5ee2f382b3
FIX 'NoneType' object has no attribute 'isalpha' ( #2440 )
...
Traceback (most recent call last):
File "/root/miniconda3/envs/sensevoice/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/root/miniconda3/envs/sensevoice/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/data2/workspace/egs_vocal_extractor/data/speech_det.py", line 156, in process_audio_task
res = model.generate(
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 306, in generate
return self.inference_with_vad(input, input_len=input_len, **cfg)
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 464, in inference_with_vad
results = self.inference(
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 345, in inference
res = model.inference(**batch, **kwargs)
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/models/sense_voice/model.py", line 950, in inference
timestamp = self.post(timestamp)
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/models/sense_voice/model.py", line 973, in post
elif prev_word.isalpha() and prev_word.isascii() and word.isalpha() and word.isascii():
AttributeError: 'NoneType' object has no attribute 'isalpha'
2025-03-20 23:01:05 +08:00
Han Zhang
3c349ac053
fix: use converted token_ids for alignment for sensevoice model with timestamp output ( #2429 )
...
* fix: use converted token_ids for alignment
BPE doesn't guarantee converted ids (subwords) are revertible. which means `tokens` converted back is not always the same as `token_int`. A easy fix is to directly use the converted ids for alignment. Since they are from the same text, it shouldn't matter.
* fix: handle empty string
to index an empty string is to raise an exception. 这里没有判空。
2025-03-18 11:45:37 +08:00
hohaiuhsx
6fe10a8dbf
修复 当选用SenseVoice模型处理长音频（同时开启vad和output_timestamp）时的异常 ( #2413 )
2025-03-10 23:16:22 +08:00
zhifu gao
3f8294b9d7
Revert "shfit to shift ( #2266 )" ( #2336 )
...
This reverts commit 1367973f98
2024-12-25 17:16:11 +08:00
Zhanzhao (Deo) Liang
8c7b7e5feb
fix export_meta import of sense voice ( #2334 )
2024-12-25 16:40:29 +08:00
Rin Arakaki
1367973f98
shfit to shift ( #2266 )
2024-12-24 17:51:31 +08:00
游雁
bb0017a686
bugfix
2024-12-12 11:35:06 +08:00
shixian
026b8e3fdc
update sensevoice small with timestamp
2024-12-05 19:29:19 +08:00
pointerhacker and zhaochaojin
70645e4807
数据并行可能导致的模型训练报错 ( #2139 )
...
* fix: 修复数据并行训练中ä¼可能会出现的错误
* fix: 修复数据并行训练中ä¼可能会出现的错误
* fix: 修复数据并行ènot need tensor
---------
Co-authored-by: zhaochaojin <[email protected]
2024-10-15 17:50:51 +08:00
游雁
fc547e14e8
bugfix memory leaky
2024-09-25 15:26:14 +08:00
北念
8aa01036b6
fix sensevoice loss_rich
2024-07-24 19:09:02 +08:00
维石
2ae59b6ce0
ONNX and torchscript export for sensevoice
2024-07-22 16:58:27 +08:00
gaochangfeng and 常材
340c55838b
EMO_UNK禁用和Merge VAD修复 ( #1940 )
...
* 添加富文本解码约束
* special token
* bug fix
* fix
* 增加unk score的参数
* emobaned
* kwargs2cfg
* merge_vad bug fix
---------
Co-authored-by: 常材 <[email protected]
2024-07-22 15:28:27 +08:00
游雁
0170f534b0
sensevoice
2024-07-05 00:17:06 +08:00
游雁
92b14aaa2a
update
2024-07-01 11:25:23 +08:00
游雁
a456ab57a8
update
2024-07-01 11:15:08 +08:00
+8
abb33d6b20
Dev gzf deepspeed ( #1844 )
...
* total_time/accum_grad
* fp16
* update with main (#1817 )
* add cmakelist
* add paraformer-torch
* add debug for funasr-onnx-offline
* fix redefinition of jieba StdExtension.hpp
* add loading torch models
* update funasr-onnx-offline
* add SwitchArg for wss-server
* add SwitchArg for funasr-onnx-offline
* update cmakelist
* update funasr-onnx-offline-rtf
* add define condition
* add gpu define for offlne-stream
* update com define
* update offline-stream
* update cmakelist
* update func CompileHotwordEmbedding
* add timestamp for paraformer-torch
* add C10_USE_GLOG for paraformer-torch
* update paraformer-torch
* fix func FunASRWfstDecoderInit
* update model.h
* fix func FunASRWfstDecoderInit
* fix tpass_stream
* update paraformer-torch
* add bladedisc for funasr-onnx-offline
* update comdefine
* update funasr-wss-server
* add log for torch
* fix GetValue BLADEDISC
* fix log
* update cmakelist
* update warmup to 10
* update funasrruntime
* add batch_size for wss-server
* add batch for bins
* add batch for offline-stream
* add batch for paraformer
* add batch for offline-stream
* fix func SetBatchSize
* add SetBatchSize for model
* add SetBatchSize for model
* fix func Forward
* fix padding
* update funasrruntime
* add dec reset for batch
* set batch default value
* add argv for CutSplit
* sort frame_queue
* sorted msgs
* fix FunOfflineInfer
* add dynamic batch for fetch
* fix FetchDynamic
* update run_server.sh
* update run_server.sh
* cpp http post server support (#1739 )
* add cpp http server
* add some comment
* remove some comments
* del debug infos
* restore run_server.sh
* adapt to new model struct
* 修复了onnxruntime在macos下编译失败的错误 (#1748 )
* Add files via upload
增加macos的编译支持
* Add files via upload
增加macos支持
* Add files via upload
target_link_directories(funasr PUBLIC ${ONNXRUNTIME_DIR}/lib)
target_link_directories(funasr PUBLIC ${FFMPEG_DIR}/lib)
添加 if(APPLE) 限制
---------
Co-authored-by: Yabin Li <[email protected] #1764 )
当语音识别结果包含 `http` 时，标点符号预测会把它会被当成 url
* fix empty asr result (#1765 )
解码结果为空的语音片段，text 用空字符串
* update export
* update export
* docs
* docs
* update export name
* docs
* update
* docs
* docs
* keep empty speech result (#1772 )
* docs
* docs
* update wechat QRcode
* Add python funasr api support for websocket srv (#1777 )
* add python funasr_api supoort
* change little to README.md
* add core tools stream
* modified a little
* fix bug for timeout
* support for buffer decode
* add ffmpeg decode for buffer
* libtorch demo
* update libtorch infer
* update utils
* update demo
* update demo
* update libtorch inference
* update model class
* update seaco paraformer
* bug fix
* bug fix
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* Dev gzf exp (#1785 )
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* dynamic batch
* start_data_split_i=0
* total_time/accum_grad
* total_time/accum_grad
* total_time/accum_grad
* update avg slice
* update avg slice
* sensevoice sanm
* sensevoice sanm
* sensevoice sanm
---------
Co-authored-by: 北念 <[email protected] #1790 )
* add cif_v1 and cif_export
* Update SDK_advanced_guide_offline_zh.md
* add cif_wo_hidden_v1
* [fix] fix empty asr result (#1794 )
* english timestamp for valilla paraformer
* wechat
* [fix] better solution for handling empty result (#1796 )
* update scripts
* modify the qformer adaptor (#1804 )
Co-authored-by: nichongjia-2007 <[email protected] #1806 )
Co-authored-by: haoneng.lhn <[email protected] #1813 )
Co-authored-by: ZihanLiao <[email protected] #1811 )
* Update cif_predictor.py
* modify cif_v1_export
under extreme cases, max_label_len calculated by batch_len misaligns with token_num
* Update cif_predictor.py
torch.cumsum precision degradation, using float64 instead
* update code
---------
Co-authored-by: 雾聪 <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] #1836 )
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* update (#1841 )
* v1.0.28
* version checker
* version checker
* rollback cif_v1 for training bug
* fixbug
* fixbug for cif
* fixbug
---------
Co-authored-by: 维石 <[email protected] #1842 )
* v1.0.28
* version checker
* version checker
* rollback cif_v1 for training bug
* fixbug
* fixbug for cif
* fixbug
---------
Co-authored-by: 维石 <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
2024-06-24 17:06:21 +08:00
游雁
45d7aa9004
decoding
2024-06-19 10:26:40 +08:00
Shi Xian
6c467e6f0a
Merge pull request #1825 from modelscope/dev_libt
...
Dev libt
2024-06-18 10:01:56 +08:00
维石
9377eed41e
update code
2024-06-17 20:20:00 +08:00
北念
ada76b6312
sensevoice
2024-06-17 13:36:22 +08:00
游雁
59bc02b089
decoding
2024-06-14 13:59:49 +08:00
游雁
67329a74a5
decoding
2024-06-14 11:04:49 +08:00
32e7836645
update with main ( #1786 )
...
* add cmakelist
* add paraformer-torch
* add debug for funasr-onnx-offline
* fix redefinition of jieba StdExtension.hpp
* add loading torch models
* update funasr-onnx-offline
* add SwitchArg for wss-server
* add SwitchArg for funasr-onnx-offline
* update cmakelist
* update funasr-onnx-offline-rtf
* add define condition
* add gpu define for offlne-stream
* update com define
* update offline-stream
* update cmakelist
* update func CompileHotwordEmbedding
* add timestamp for paraformer-torch
* add C10_USE_GLOG for paraformer-torch
* update paraformer-torch
* fix func FunASRWfstDecoderInit
* update model.h
* fix func FunASRWfstDecoderInit
* fix tpass_stream
* update paraformer-torch
* add bladedisc for funasr-onnx-offline
* update comdefine
* update funasr-wss-server
* add log for torch
* fix GetValue BLADEDISC
* fix log
* update cmakelist
* update warmup to 10
* update funasrruntime
* add batch_size for wss-server
* add batch for bins
* add batch for offline-stream
* add batch for paraformer
* add batch for offline-stream
* fix func SetBatchSize
* add SetBatchSize for model
* add SetBatchSize for model
* fix func Forward
* fix padding
* update funasrruntime
* add dec reset for batch
* set batch default value
* add argv for CutSplit
* sort frame_queue
* sorted msgs
* fix FunOfflineInfer
* add dynamic batch for fetch
* fix FetchDynamic
* update run_server.sh
* update run_server.sh
* cpp http post server support (#1739 )
* add cpp http server
* add some comment
* remove some comments
* del debug infos
* restore run_server.sh
* adapt to new model struct
* 修复了onnxruntime在macos下编译失败的错误 (#1748 )
* Add files via upload
增加macos的编译支持
* Add files via upload
增加macos支持
* Add files via upload
target_link_directories(funasr PUBLIC ${ONNXRUNTIME_DIR}/lib)
target_link_directories(funasr PUBLIC ${FFMPEG_DIR}/lib)
添加 if(APPLE) 限制
---------
Co-authored-by: Yabin Li <[email protected] #1764 )
当语音识别结果包含 `http` 时，标点符号预测会把它会被当成 url
* fix empty asr result (#1765 )
解码结果为空的语音片段，text 用空字符串
* docs
* docs
* docs
* docs
* docs
* keep empty speech result (#1772 )
* docs
* docs
* update wechat QRcode
* Add python funasr api support for websocket srv (#1777 )
* add python funasr_api supoort
* change little to README.md
* add core tools stream
* modified a little
* fix bug for timeout
* support for buffer decode
* add ffmpeg decode for buffer
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* auto frontend
* Dev gzf exp (#1785 )
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* dynamic batch
* start_data_split_i=0
* total_time/accum_grad
* total_time/accum_grad
* total_time/accum_grad
* update avg slice
* update avg slice
* sensevoice sanm
* sensevoice sanm
* sensevoice sanm
---------
Co-authored-by: 北念 <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
2024-06-06 09:54:35 +08:00
zhifu gao and 北念
db9ec58cb4
Dev gzf exp ( #1785 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* dynamic batch
* start_data_split_i=0
* total_time/accum_grad
* total_time/accum_grad
* total_time/accum_grad
* update avg slice
* update avg slice
* sensevoice sanm
* sensevoice sanm
* sensevoice sanm
---------
Co-authored-by: 北念 <[email protected]
2024-06-05 17:30:57 +08:00
游雁
79b09f1d67
auto frontend
2024-06-05 17:22:21 +08:00
961ec280af
Dev gzf deepspeed ( #1736 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* dynamic batch
* start_data_split_i=0
* total_time/accum_grad
* total_time/accum_grad
* total_time/accum_grad
* update avg slice
* update avg slice
* sensevoice sanm
* sensevoice sanm
* add
* add
* add
* add
* deepspeed
* update with main (#1731 )
* c++ runtime adapt to 1.0 (#1724 )
* adapt vad runtime to 1.0
* add json
* change yml name
* add func LoadVocabFromJson
* add token file for InitAsr
* add token path for OfflineStream
* add funcOpenYaml
* add token file for InitPunc
* add token file for stream
* update punc-model
* update funasr-wss-server
* update runtime_sdk_download_tool.py
* update docker list
* Delete docs/images/wechat.png
* Add files via upload
* Emo2Vec限定选择的情感类别 (#1730 )
* 限定选择的情感类别
* 使用none来禁用情感标签输出
* 修改输出接口
* 使用unuse来禁用token
---------
Co-authored-by: 常材 <[email protected] #1680 )
---------
Co-authored-by: Yabin Li <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
2024-05-20 15:31:46 +08:00
a0f03bd2a8
Dev gzf deepspeed ( #1732 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* dynamic batch
* start_data_split_i=0
* total_time/accum_grad
* total_time/accum_grad
* total_time/accum_grad
* update avg slice
* update avg slice
* sensevoice sanm
* sensevoice sanm
* add
* add
* add
* add
* deepspeed
* update with main (#1731 )
* c++ runtime adapt to 1.0 (#1724 )
* adapt vad runtime to 1.0
* add json
* change yml name
* add func LoadVocabFromJson
* add token file for InitAsr
* add token path for OfflineStream
* add funcOpenYaml
* add token file for InitPunc
* add token file for stream
* update punc-model
* update funasr-wss-server
* update runtime_sdk_download_tool.py
* update docker list
* Delete docs/images/wechat.png
* Add files via upload
* Emo2Vec限定选择的情感类别 (#1730 )
* 限定选择的情感类别
* 使用none来禁用情感标签输出
* 修改输出接口
* 使用unuse来禁用token
---------
Co-authored-by: 常材 <[email protected] #1680 )
---------
Co-authored-by: Yabin Li <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
2024-05-15 19:48:50 +08:00
游雁
c7bfd1fdc5
bugfix
2024-05-15 16:40:12 +08:00
zhifu gao
4adb76a6ed
Dev gzf exp ( #1707 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* dynamic batch
2024-05-08 19:21:58 +08:00
zhifu gao and 常材
a7bc099548
Dev gzf exp ( #1705 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
* Gcf (#1704 )
* 添加富文本解码约束
* special token
* bug fix
* fix
---------
Co-authored-by: 常材 <[email protected] [email protected]
2024-05-08 17:32:36 +08:00
zhifu gao
b1c186fd00
Dev gzf exp ( #1700 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
* wechat
* decoding key
* decoding key
* decoding key
* decoding key
* decoding key
2024-05-08 00:31:29 +08:00
zhifu gao
7be2a1d7e4
Dev gzf exp ( #1696 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
* decoding
2024-05-06 22:36:00 +08:00
zhifu gao
00d0df3a10
Dev gzf decoding ( #1695 )
...
* resume from step
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* batch
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* train_loss_avg train_acc_avg
* log step
* wav is not exist
* wav is not exist
* decoding
* decoding
2024-05-06 22:17:25 +08:00
zhifu gao
a09aba419f
Dev gzf exp ( #1682 )
...
* resume from step
2024-04-30 12:52:58 +08:00
zhifu gao
11cf10e433
Dev gzf exp ( #1678 )
...
* resume from step
* batch
* batch
* batch
2024-04-29 14:52:20 +08:00
zhifu gao
1cdb3cc28d
Dev gzf exp ( #1665 )
...
* rwkv 5
* rwkv v4
* rwkv v4
* rwkv
* rwkv
* update
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
* resume from step
2024-04-26 11:27:39 +08:00
LauraGPT