志浩
|
0fa8e2976f
|
add extract token run_mode
|
2024-09-24 17:03:17 +08:00 |
|
志浩
|
6fc9354924
|
add text ibest writer for SenseVoiceL
|
2024-09-24 16:32:01 +08:00 |
|
志浩
|
797bd57f91
|
add text ibest writer for SenseVoiceL
|
2024-09-24 15:54:42 +08:00 |
|
游雁
|
d45230c6ba
|
batch
|
2024-09-21 11:46:52 +08:00 |
|
游雁
|
204fcd7900
|
batch
|
2024-09-21 11:29:53 +08:00 |
|
志浩
|
829b1f8c72
|
redo:fix mp3 bug
|
2024-09-18 23:04:25 +08:00 |
|
shixian.shi
|
9edbcd5420
|
Merge branch dzh_straming_test into dev_gzf_deepspeed
Title: align others with dev_gzf_deepspeed
本次代码评审主要涉及添加CTC模块、优化MP3编码处理、简化音素令牌处理和引入新库,旨在增强模型的语音识别与文本转语音功能,同时改进音频处理逻辑。
Link: https://code.alibaba-inc.com/zhifu.gzf/FunASR/codereview/18421381
|
2024-09-18 22:26:21 +08:00 |
|
zhifu.gzf
|
60bc4176c2
|
feat: Resolve conflict, auto committed by CodeFlow
|
2024-09-18 22:23:45 +08:00 |
|
志浩
|
79c188be33
|
align others with dev_gzf_deepspeed
|
2024-09-18 18:15:32 +08:00 |
|
志浩
|
7edf6a30d9
|
align others with dev_gzf_deepspeed
|
2024-09-18 18:10:07 +08:00 |
|
志浩
|
669fedef82
|
align others with dev_gzf_deepspeed
|
2024-09-18 18:04:35 +08:00 |
|
志浩
|
f0da9da31d
|
add lameenc mp3 encoder for 4o
|
2024-09-18 17:42:07 +08:00 |
|
志浩
|
f32b1c1bdc
|
add cross fade for 4o
|
2024-09-18 16:51:55 +08:00 |
|
志浩
|
e8ad966fa7
|
add cross fade for 4o
|
2024-09-18 16:47:12 +08:00 |
|
志浩
|
c1a4abe273
|
add cross fade for 4o
|
2024-09-18 16:44:24 +08:00 |
|
志浩
|
8df772de10
|
add cross fade for 4o
|
2024-09-18 16:40:35 +08:00 |
|
志浩
|
f7fa394bb1
|
add cross fade for 4o
|
2024-09-18 16:15:34 +08:00 |
|
志浩
|
cf6d7249d7
|
add cross fade for 4o
|
2024-09-18 16:09:43 +08:00 |
|
志浩
|
6e4362ac1f
|
add cross fade for 4o
|
2024-09-18 15:47:50 +08:00 |
|
志浩
|
f3d43be322
|
add cross fade for 4o
|
2024-09-18 15:29:51 +08:00 |
|
志浩
|
cb30c8fabb
|
add cross fade for 4o
|
2024-09-18 15:17:52 +08:00 |
|
志浩
|
4d001cc185
|
add cross fade for 4o
|
2024-09-18 15:14:52 +08:00 |
|
志浩
|
579d7b1e46
|
add cross fade for 4o
|
2024-09-18 14:33:24 +08:00 |
|
志浩
|
196b720d06
|
add cross fade for 4o
|
2024-09-18 14:21:52 +08:00 |
|
志浩
|
58b52b344e
|
add cross fade for 4o
|
2024-09-18 14:17:12 +08:00 |
|
志浩
|
f7435706a9
|
add cross fade for 4o
|
2024-09-18 14:14:24 +08:00 |
|
志浩
|
814dc25492
|
add cross fade for 4o
|
2024-09-18 13:59:14 +08:00 |
|
志浩
|
2c3ae95bbf
|
Merge branch 'dev_gzf_deepspeed' of gitlab.alibaba-inc.com:zhifu.gzf/FunASR into dev_gzf_deepspeed
|
2024-09-18 11:00:27 +08:00 |
|
志浩
|
e9557a0ee7
|
insert VQ into sensevoice encoder
|
2024-09-18 11:00:16 +08:00 |
|
木守
|
c562fa8b01
|
update
|
2024-09-16 20:02:05 +08:00 |
|
木守
|
2590bb5b8b
|
update
|
2024-09-15 10:19:52 +08:00 |
|
木守
|
ca5def5d24
|
update
|
2024-09-15 10:14:40 +08:00 |
|
木守
|
0efc5c4dbf
|
Merge branch 'dev_gzf_deepspeed' of http://gitlab.alibaba-inc.com/zhifu.gzf/FunASR into dev_gzf_deepspeed
|
2024-09-14 20:22:44 +08:00 |
|
木守
|
8df4b1001e
|
update
|
2024-09-14 20:22:37 +08:00 |
|
游雁
|
11023eea21
|
speech2speech
|
2024-09-14 14:47:32 +08:00 |
|
游雁
|
21016fc693
|
Merge branch 'dev_gzf_deepspeed' of gitlab.alibaba-inc.com:zhifu.gzf/FunASR into dev_gzf_deepspeed
merge
|
2024-09-14 14:41:01 +08:00 |
|
游雁
|
cd67bf6c73
|
speech2speech
|
2024-09-14 14:23:36 +08:00 |
|
志浩
|
6fdba0822e
|
simple streaming
|
2024-09-13 17:26:36 +08:00 |
|
志浩
|
6c59692f71
|
remove set_all_random_seed
|
2024-09-13 17:23:44 +08:00 |
|
志浩
|
4b00bc61e9
|
simple streaming
|
2024-09-13 17:15:39 +08:00 |
|
志浩
|
4a8cb6f0c4
|
simple streaming
|
2024-09-13 16:24:06 +08:00 |
|
志浩
|
441b997f19
|
simple streaming
|
2024-09-13 16:13:40 +08:00 |
|
志浩
|
8b56cc9ba5
|
simple streaming
|
2024-09-13 15:44:39 +08:00 |
|
志浩
|
e5696954a9
|
simple streaming
|
2024-09-13 15:36:50 +08:00 |
|
游雁
|
89c1dd5f08
|
Merge branch 'dev_gzf_deepspeed' of gitlab.alibaba-inc.com:zhifu.gzf/FunASR into dev_gzf_deepspeed
merge
|
2024-09-13 14:36:24 +08:00 |
|
游雁
|
c66054ef63
|
speech2speech
|
2024-09-13 14:35:53 +08:00 |
|
志浩
|
d82cfa21a5
|
cut paragraph for streaming s2s
|
2024-09-13 11:03:38 +08:00 |
|
志浩
|
8a06c8d44e
|
cut paragraph for streaming s2s
|
2024-09-13 10:36:34 +08:00 |
|
志浩
|
4b65ccee2a
|
cut paragraph for streaming s2s
|
2024-09-12 19:51:43 +08:00 |
|
志浩
|
77b75ae3b2
|
cut paragraph for streaming s2s
|
2024-09-12 19:34:42 +08:00 |
|