ac7e3ee8a2
fix: revert inference_batch_size for non-Paraformer models
...
Conformer, Transformer, and Branchformer models raise
NotImplementedError for batch decoding. Only Paraformer and
e_paraformer support batch_size>1 for inference. Revert the
non-Paraformer recipes back to batch_size=1.
2026-05-24 01:54:05 +08:00
0cbf26e0c7
fix: increase inference_batch_size from 1 to 32 in aishell recipes
...
The conformer, transformer, branchformer, and e_branchformer recipes
had inference_batch_size=1 which made GPU decoding extremely slow
(processing one utterance at a time). Changed to 32 to match the
paraformer recipe and utilize GPU parallelism during inference.
2026-05-23 21:21:02 +08:00
b5ad7c81be
Support eparaformer model on aishell1 recipe ( #2327 )
2024-12-21 17:13:46 +08:00
f47d43c020
Dev gzf deepspeed ( #1750 )
...
* 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 <gaochangfeng.gcf@alibaba-inc.com >
* bugfix
* v1.0.27
* update docs
* hf hub
* Fix incorrect assignment of 'end' attribute to 'start' in sentences list comprehension (#1680 )
---------
Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com >
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com >
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com >
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com >
* docs
* docs
* deepspeed
* deepspeed
* deepspeed
* deepspeed
* update
* ds
* ds
* ds
* ds
* ds
* ds
* ds
* add
* add
* bugfix
* add
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
* wenetspeech
---------
Co-authored-by: Yabin Li <wucong.lyb@alibaba-inc.com >
Co-authored-by: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com >
Co-authored-by: 常材 <gaochangfeng.gcf@alibaba-inc.com >
Co-authored-by: nsdou <168500039+nsdou@users.noreply.github.com >
2024-05-23 09:57:14 +08:00
a09aba419f
Dev gzf exp ( #1682 )
...
* resume from step
2024-04-30 12:52:58 +08:00
861147c730
Dev gzf exp ( #1654 )
...
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* bugfix
* update with main (#1631 )
* update seaco finetune
* v1.0.24
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com >
* sensevoice
* sensevoice
* sensevoice
* update with main (#1638 )
* update seaco finetune
* v1.0.24
* update rwkv template
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com >
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* sense voice
* whisper
* whisper
* update style
* update style
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com >
2024-04-24 16:03:38 +08:00
0a4a1d5257
Dev gzf exp ( #1645 )
...
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* sensevoice finetune
* bugfix
* update with main (#1631 )
* update seaco finetune
* v1.0.24
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com >
* sensevoice
* sensevoice
* sensevoice
* update with main (#1638 )
* update seaco finetune
* v1.0.24
* update rwkv template
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com >
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sensevoice
* sense voice
* sense voice
* sense voice
* sense voice
---------
Co-authored-by: 维石 <shixian.shi@alibaba-inc.com >
2024-04-23 12:48:52 +08:00
48693b45c0
Dev gzf new ( #1574 )
...
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* whisper_lib for sense voice
* aishell recipe
* sense voice
* docs
2024-04-02 10:33:27 +08:00
6fa8ee48e1
Dev gzf new ( #1567 )
...
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* whisper_lib for sense voice
* aishell recipe
2024-03-30 10:13:42 +08:00
8071728f17
Dev gzf new ( #1559 )
...
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
* train
2024-03-28 15:31:39 +08:00
08392f28ec
train
2024-03-27 17:06:26 +08:00
46ec82c054
update
2024-03-26 16:47:10 +08:00
cc47491099
update
2024-03-26 12:54:12 +08:00
97dd199b38
train
2024-03-25 23:01:19 +08:00
81fb78286f
update
2024-03-22 20:13:05 +08:00
d5c98e6f65
update
2024-03-22 19:40:54 +08:00
fcbbe8af9f
update
2024-03-22 19:25:29 +08:00
20c35cdbc7
Dev gzf ( #1379 )
...
* update train recipe
* v1.0.8
* llm
* update trainer
* update trainer
* update trainer
* train finetune demo
* train finetune demo
2024-02-22 12:07:30 +08:00
f91205399f
update train recipe
2024-02-21 14:41:08 +08:00
26ab38b56c
update train recipe
2024-02-21 14:22:14 +08:00
75f22337b8
bugfix
2024-02-21 14:13:58 +08:00
cab0af88d8
bugfix
2024-02-21 13:47:50 +08:00
497edf4c9d
bugfix
2024-02-21 11:30:59 +08:00
4cf44a89f8
bugfix
2024-02-21 00:43:27 +08:00
c0011994f0
train finetune
2024-02-20 19:36:18 +08:00
96e4ff1870
train finetune
2024-02-20 18:38:51 +08:00
2e8dc0933f
train finetune
2024-02-20 18:01:15 +08:00
45d9ccafef
train finetune
2024-02-20 17:48:53 +08:00
bc19499b48
update
2024-02-20 16:22:53 +08:00
6c8e839742
update
2024-02-20 15:53:06 +08:00
362a6de3c8
update
2024-02-20 15:22:13 +08:00
df9d3438da
update
2024-02-20 14:35:51 +08:00
f3c79b4968
update
2024-02-20 14:05:11 +08:00
6f3005e063
aishell example
2024-02-19 22:16:12 +08:00
ce4235b1c8
aishell example
2024-02-19 22:11:49 +08:00
25fbf7110b
aishell example
2024-02-19 21:30:11 +08:00
ff4306346e
aishell example
2024-02-19 21:26:25 +08:00
4ebde3c4ac
aishell example
2024-02-19 18:42:35 +08:00
6a9c21a408
aishell example
2024-02-19 17:05:49 +08:00
1448e021ac
aishell example
2024-02-19 14:59:26 +08:00
d77910eb6d
funasr2
2023-12-11 13:42:40 +08:00
游雁