Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
pre-commit-ci[bot] c118e3217d | 5 days ago | |
---|---|---|
.github/workflows | 7 months ago | |
bert | 5 months ago | |
configs | 3 months ago | |
css | 5 months ago | |
emotional | 4 months ago | |
filelists | 5 months ago | |
for_deploy | 3 months ago | |
img | 6 months ago | |
monotonic_align | 7 months ago | |
oldVersion | 2 months ago | |
onnx_modules | 1 month ago | |
slm/wavlm-base-plus | 4 months ago | |
text | 2 months ago | |
tools | 3 months ago | |
.gitignore | 4 months ago | |
.gitmodules | 6 months ago | |
.pre-commit-config.yaml | 5 days ago | |
LICENSE | 8 months ago | |
README.md | 2 weeks ago | |
attentions.py | 7 months ago | |
bert_gen.py | 3 months ago | |
commons.py | 4 months ago | |
compress_model.py | 4 months ago | |
config.py | 3 months ago | |
data_utils.py | 4 months ago | |
default_config.yml | 3 months ago | |
export_onnx.py | 1 month ago | |
hiyoriUI.py | 3 months ago | |
infer.py | 3 months ago | |
losses.py | 4 months ago | |
mel_processing.py | 5 months ago | |
models.py | 4 months ago | |
modules.py | 1 month ago | |
onnx_infer.py | 4 months ago | |
preprocess_text.py | 4 months ago | |
re_matching.py | 4 months ago | |
requirements.txt | 3 months ago | |
resample.py | 4 months ago | |
resample_legacy.py | 4 months ago | |
run_MnodesAndMgpus.sh | 5 months ago | |
spec_gen.py | 5 months ago | |
train_ms.py | 3 months ago | |
transforms.py | 7 months ago | |
update_status.py | 3 months ago | |
utils.py | 4 months ago | |
webui.py | 3 months ago | |
webui_preprocess.py | 4 months ago |
VITS2 Backbone with multilingual bert
For quick guide, please refer to webui_preprocess.py
.
简易教程请参见 webui_preprocess.py
。
FishAudio下的全新自回归TTS Fish-Speech目前已经开始着手进行LLM大规模预训练工作。我们目前需要相对高质量的语音文件以进行最后的SFT(监督微调),因此在这里进行公开征集。
贡献的语音数据需要满足以下要求:
1.总时长>10h
2.需要是中文或者英文素材
3.不得存在伴奏,可以使用UVR素材
4.带文本优先,不带亦可
5.咬字清楚,无明显口音
如果您有符合上述条件的素材且愿意贡献于训练,请直接联系QQ 2225664821。
我们会对最终模型进行技术手段的处理,使之无法合成您素材对应的speaker音频。
您的贡献届时将会记录在贡献清单上,随release发布。
FishAudio Team
No Description
Python Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》