deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
lyuxiang.lx
2024-10-16 12:59:57 +08:00
parent ea7d709fbb
commit 555efd0301
3 changed files with 2 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -26,9 +26,7 @@ For `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVo
- [ ] 25hz llama based llm model which supports lora finetune - [ ] 25hz llama based llm model which supports lora finetune
- [ ] Support more instruction mode - [ ] Support more instruction mode
- [ ] Voice conversion
- [ ] Music generation - [ ] Music generation
- [ ] Training script sample based on Mandarin
- [ ] CosyVoice-500M trained with more multi-lingual data - [ ] CosyVoice-500M trained with more multi-lingual data
- [ ] More... - [ ] More...
@@ -113,7 +111,7 @@ from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav from cosyvoice.utils.file_utils import load_wav
import torchaudio import torchaudio
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT') cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=True, load_onnx=False, fp16=True)
# sft usage # sft usage
print(cosyvoice.list_avaliable_spks()) print(cosyvoice.list_avaliable_spks())
# change stream=True for chunk stream inference # change stream=True for chunk stream inference

2
cosyvoice/bin/train.py
View File

@@ -74,7 +74,7 @@ def get_args():
choices=['model_only', 'model+optimizer'], choices=['model_only', 'model+optimizer'],
help='save model/optimizer states') help='save model/optimizer states')
parser.add_argument('--timeout', parser.add_argument('--timeout',
default=30, default=60,
type=int, type=int,
help='timeout (in seconds) of cosyvoice_join.') help='timeout (in seconds) of cosyvoice_join.')
parser = deepspeed.add_config_arguments(parser) parser = deepspeed.add_config_arguments(parser)

1
examples/libritts/cosyvoice/run.sh
View File

@@ -99,7 +99,6 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
--num_workers ${num_workers} \ --num_workers ${num_workers} \
--prefetch ${prefetch} \ --prefetch ${prefetch} \
--pin_memory \ --pin_memory \
--timeout 300 \
--deepspeed_config ./conf/ds_stage2.json \ --deepspeed_config ./conf/ds_stage2.json \
--deepspeed.save_states model+optimizer --deepspeed.save_states model+optimizer
done done