Hugging Face's logo

AXERA-TECH
/
CosyVoice2

Text-to-Speech
Transformers
ONNX
English
Chinese
CosyVoice2
Speech
Model card Files
xet
Community
lihongjie commited on
Commit
62b2796
·
1 Parent(s): 760284e

优化音质

Browse files
Files changed (12) hide show
  1. .gitattributes +12 -0
  2. README.md +1 -1
  3. main_ax650 +2 -2
  4. token2wav-axmodels/flow_encoder_28.axmodel +2 -2
  5. token2wav-axmodels/flow_encoder_53.axmodel +2 -2
  6. token2wav-axmodels/flow_encoder_78.axmodel +2 -2
  7. token2wav-axmodels/{hift_50_first.axmodel → hift_p1_50_first.mnn} +2 -2
  8. token2wav-axmodels/{hift_58.axmodel → hift_p1_58.mnn} +2 -2
  9. token2wav-axmodels/hift_p2_50_first.axmodel +3 -0
  10. token2wav-axmodels/hift_p2_58.axmodel +3 -0
  11. token2wav-axmodels/rand_noise_1_80_300.txt +0 -0
  12. token2wav-axmodels/speech_window_2x8x480.txt +0 -0
.gitattributes CHANGED
@@ -98,3 +98,15 @@ asset/en_woman1.txt filter=lfs diff=lfs merge=lfs -text
98
  asset/zh_man1.txt filter=lfs diff=lfs merge=lfs -text
99
  asset/zh_woman1.wav filter=lfs diff=lfs merge=lfs -text
100
  asset/zh_man2.txt filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  asset/zh_man1.txt filter=lfs diff=lfs merge=lfs -text
99
  asset/zh_woman1.wav filter=lfs diff=lfs merge=lfs -text
100
  asset/zh_man2.txt filter=lfs diff=lfs merge=lfs -text
101
+ prompt_files/llm_embedding.txt filter=lfs diff=lfs merge=lfs -text
102
+ prompt_files/llm_prompt_speech_token.txt filter=lfs diff=lfs merge=lfs -text
103
+ prompt_files/prompt_speech_feat.txt filter=lfs diff=lfs merge=lfs -text
104
+ prompt_files/prompt_text.txt filter=lfs diff=lfs merge=lfs -text
105
+ prompt_files/flow_embedding.txt filter=lfs diff=lfs merge=lfs -text
106
+ prompt_files/flow_prompt_speech_token.txt filter=lfs diff=lfs merge=lfs -text
107
+ token2wav-axmodels/hift_p1_58.mnn filter=lfs diff=lfs merge=lfs -text
108
+ token2wav-axmodels/hift_p2_50_first.axmodel filter=lfs diff=lfs merge=lfs -text
109
+ token2wav-axmodels/hift_p2_58.axmodel filter=lfs diff=lfs merge=lfs -text
110
+ token2wav-axmodels/rand_noise_1_80_300.txt filter=lfs diff=lfs merge=lfs -text
111
+ token2wav-axmodels/speech_window_2x8x480.txt filter=lfs diff=lfs merge=lfs -text
112
+ token2wav-axmodels/hift_p1_50_first.mnn filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -139,7 +139,7 @@ modelscope download --model pengzhendong/wetext --local_dir pengzhendong/wetext
139
  ##### (2). Process Prompt Speech
140
  Example:
141
  ```
142
- python scripts/process_prompt.py --prompt_text asset/zh_man1.txt --prompt_speech asset/zh_man1.mp3 --output zh_man1
143
  ```
144
 
145
  Pass parameters according to the actual situation.
 
139
  ##### (2). Process Prompt Speech
140
  Example:
141
  ```
142
+ python scripts/process_prompt.py --prompt_text asset/zh_man1.txt --prompt_speech asset/zh_man1.wav --output zh_man1
143
  ```
144
 
145
  Pass parameters according to the actual situation.
main_ax650 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d36bca7a681437db6ece77226fa6e00605d613b2ab7028de50cd525ec6575c6
3
- size 6641632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6559030b28a84f4a726a53b526f4ec8ae7f73fd4a8c249631eb88c98062a2958
3
+ size 9587560
token2wav-axmodels/flow_encoder_28.axmodel CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbd813e5258e8955ccc607c29a40ff5e613e392374598a64d21dff0b73752d28
3
- size 41944026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017195d57340881889812f4fb4532a3f5094d43bd2252789f8f9997a9f096de6
3
+ size 41732066
token2wav-axmodels/flow_encoder_53.axmodel CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8af4794d4e79b2322dd127c153ed721c7f3de84c883d5b24ae471079d649c66
3
- size 42722593
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7eea4e2b6cbc3cf6b4a8b0630114bee99b158debdc9037d807bd2d82f458c87
3
+ size 42512649
token2wav-axmodels/flow_encoder_78.axmodel CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a1e7df9b67e0d80f1cddc11c0d5fd22ab63f1d5e7f9f1f1ff0667fdc2896b1b
3
- size 43528184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae680034a702fb0ff6010c48269b0fdbb3c6dc3067f1af3445645f1257fee9a2
3
+ size 43411488
token2wav-axmodels/{hift_50_first.axmodel → hift_p1_50_first.mnn} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:524fbe2a9b8eccf8a9d005592a54f99bc49770606baf267361a6db093cfa019e
3
- size 26780419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60ce058f202d0c50c4fd1f8998409f6485bfa1a02dd92a9c6a5af09aa87ce4b
3
+ size 13098956
token2wav-axmodels/{hift_58.axmodel → hift_p1_58.mnn} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b4ba058d80408e69d307582e02196ba061dc3f9595e0ef688d14f63510a4156
3
- size 26812050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09dc4b29d4a461728c6cf9d3714da6ba36271d1131d2bd4ce03c7656209c4dc
3
+ size 13098948
token2wav-axmodels/hift_p2_50_first.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18ba9d31e134309d790b6d292acead32eb3fe607d0fe53afec07414f5fb6ddb
3
+ size 23163948
token2wav-axmodels/hift_p2_58.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478be32a8f90a2cb6f478a1c48a28d88d46e9c25ed417a4718f67ad225b4f286
3
+ size 22876535
token2wav-axmodels/rand_noise_1_80_300.txt CHANGED
The diff for this file is too large to render. See raw diff
 
token2wav-axmodels/speech_window_2x8x480.txt CHANGED
The diff for this file is too large to render. See raw diff