UniqAI/openedai-speech
1
0
Fork 0
mirror of https://github.com/matatonic/openedai-speech synced 2025-06-26 18:16:32 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

0.17.1

Browse Source
This commit is contained in:
matatonic 2024-07-01 19:43:32 -04:00
parent 02a6c7eb3e
commit fdd443b10f
5 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -30,6 +30,11 @@ If you find a better voice match for `tts-1` or `tts-1-hd`, please let me know s
## Recent Changes ## Recent Changes
Version 0.17.1, 2024-07-01
* fix ROCm (add langdetect to requirements-rocm.txt)
* Fix zh-cn for xtts
Version 0.17.0, 2024-07-01 Version 0.17.0, 2024-07-01
* Automatic language detection, thanks [@RodolfoCastanheira](https://github.com/RodolfoCastanheira) * Automatic language detection, thanks [@RodolfoCastanheira](https://github.com/RodolfoCastanheira)

4
add_voice.py
View File

@ -11,8 +11,8 @@ parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFo
parser.add_argument('sample', action='store', help="Set the wav sample file") parser.add_argument('sample', action='store', help="Set the wav sample file")
parser.add_argument('-n', '--name', action='store', help="Set the name for the voice (by default will use the WAV file name)") parser.add_argument('-n', '--name', action='store', help="Set the name for the voice (by default will use the WAV file name)")
parser.add_argument('-l', '--language', action='store', default="en", help="Set the language for the voice", parser.add_argument('-l', '--language', action='store', default="auto", help="Set the language for the voice",
choices=['en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko']) choices=['auto', 'en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko', 'hi'])
parser.add_argument('--openai-model', action='store', default="tts-1-hd", help="Set the openai model for the voice") parser.add_argument('--openai-model', action='store', default="tts-1-hd", help="Set the openai model for the voice")
parser.add_argument('--xtts-model', action='store', default="xtts", help="Set the xtts model for the voice (if using a custom model, also set model_path)") parser.add_argument('--xtts-model', action='store', default="xtts", help="Set the xtts model for the voice (if using a custom model, also set model_path)")
parser.add_argument('--model-path', action='store', default=None, help="Set the path for a custom xtts model") parser.add_argument('--model-path', action='store', default=None, help="Set the path for a custom xtts model")

1
requirements-rocm.txt
View File

@ -3,6 +3,7 @@ uvicorn
loguru loguru
piper-tts piper-tts
coqui-tts coqui-tts
langdetect
# Creating an environment where deepspeed works is complex, for now it will be disabled by default. # Creating an environment where deepspeed works is complex, for now it will be disabled by default.
#deepspeed #deepspeed
torch; --index-url https://download.pytorch.org/whl/rocm5.7; sys_platform == "linux" torch; --index-url https://download.pytorch.org/whl/rocm5.7; sys_platform == "linux"

6
speech.py
View File

@ -296,7 +296,11 @@ async def generate_speech(request: GenerateSpeechRequest):
hf_generate_kwargs['enable_text_splitting'] = hf_generate_kwargs.get('enable_text_splitting', True) # change the default to true hf_generate_kwargs['enable_text_splitting'] = hf_generate_kwargs.get('enable_text_splitting', True) # change the default to true
if hf_generate_kwargs['enable_text_splitting']: if hf_generate_kwargs['enable_text_splitting']:
all_text = split_sentence(input_text, language, xtts.xtts.tokenizer.char_limits[language]) if language == 'zh-cn':
split_lang = 'zh'
else:
split_lang = language
all_text = split_sentence(input_text, split_lang, xtts.xtts.tokenizer.char_limits[split_lang])
else: else:
all_text = [input_text] all_text = [input_text]

3
voice_to_speaker.default.yaml
View File

@ -46,8 +46,9 @@ tts-1-hd:
model: xtts model: xtts
speaker: voices/shimmer.wav speaker: voices/shimmer.wav
me: me:
model: xtts_v2.0.2 # you can specify different xtts version model: xtts_v2.0.2 # you can specify an older xtts version
speaker: voices/me.wav # this could be you speaker: voices/me.wav # this could be you
language: auto
enable_text_splitting: True enable_text_splitting: True
length_penalty: 1.0 length_penalty: 1.0
repetition_penalty: 10 repetition_penalty: 10