blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-04-05 04:22:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

初步版本

Browse Source
This commit is contained in:
Kenn Zhang 2024-01-22 20:21:18 +08:00
parent ca5b67002b
commit ccbc93f4fc
5 changed files with 106 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
Docker/damo.sha256 Normal file
View File

@ -0,0 +1,3 @@
5bba782a5e9196166233b9ab12ba04cadff9ef9212b4ff6153ed9290ff679025 /workspace/tools/damo_asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb
b3be75be477f0780277f3bae0fe489f48718f585f3a6e45d7dd1fbb1a4255fc5 /workspace/tools/damo_asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch/model.pb
a5818bb9d933805a916eebe41eb41648f7f9caad30b4bd59d56f3ca135421916 /workspace/tools/damo_asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/model.pb

11
Docker/download.sh Normal file
View File

@ -0,0 +1,11 @@
#!/usr/bin/env bash
set -Eeuo pipefail
echo "Downloading models..."
aria2c --disable-ipv6 --input-file /workspace/Docker/links.txt --dir /workspace --continue
echo "Checking SHA256..."
parallel --will-cite -a /workspace/Docker/links.sha256 "echo -n {} | sha256sum -c"

12
Docker/links.sha256 Normal file
View File

@ -0,0 +1,12 @@
b1c1e17e9c99547a89388f72048cd6e1b41b5a18b170e86a46dfde0324d63eb1 /workspace/GPT_SoVITS/pretrained_models/s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt
fc579c1db3c1e21b721001cf99d7a584214280df19b002e200b630a34fa06eb8 /workspace/GPT_SoVITS/pretrained_models/s2D488k.pth
020a014e1e01e550e510f2f61fae5e5f5b6aab40f15c22f1f12f724df507e835 /workspace/GPT_SoVITS/pretrained_models/s2G488k.pth
24164f129c66499d1346e2aa55f183250c223161ec2770c0da3d3b08cf432d3c /workspace/GPT_SoVITS/pretrained_models/chinese-hubert-base/pytorch_model.bin
e53a693acc59ace251d143d068096ae0d7b79e4b1b503fa84c9dcf576448c1d8 /workspace/GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/pytorch_model.bin
39796caa5db18d7f9382d8ac997ac967bfd85f7761014bb807d2543cc844ef05 /workspace/tools/uvr5/uvr5_weights/HP2_all_vocals.pth
45e6b65199e781b4a6542002699be9f19cd3d1cb7d1558bc2bfbcd84674dfe28 /workspace/tools/uvr5/uvr5_weights/HP3_all_vocals.pth
5908891829634926119720241e8573d97cbeb8277110a7512bdb0bd7563258ee /workspace/tools/uvr5/uvr5_weights/HP5_only_main_vocal.pth
8c8fd1582f9aabc363e47af62ddb88df6cae7e064cae75bbf041a067a5e0aee2 /workspace/tools/uvr5/uvr5_weights/VR-DeEchoAggressive.pth
01376dd2a571bf3cb9cced680732726d2d732609d09216a610b0d110f133febe /workspace/tools/uvr5/uvr5_weights/VR-DeEchoDeReverb.pth
56aba59db3bcdd14a14464e62f3129698ecdea62eee0f003b9360923eb3ac79e /workspace/tools/uvr5/uvr5_weights/VR-DeEchoNormal.pth
233bb5c6aaa365e568659a0a81211746fa881f8f47f82d9e864fce1f7692db80 /workspace/tools/uvr5/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx

34
Docker/links.txt Normal file
View File

@ -0,0 +1,34 @@
# GPT-SoVITS models
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/s1bert25hz-2kh-longer-epoch%3D68e-step%3D50232.ckpt
out=GPT_SoVITS/pretrained_models/s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/s2D488k.pth
out=GPT_SoVITS/pretrained_models/s2D488k.pth
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/s2G488k.pth
out=GPT_SoVITS/pretrained_models/s2G488k.pth
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-hubert-base/config.json
out=GPT_SoVITS/pretrained_models/chinese-hubert-base/config.json
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-hubert-base/preprocessor_config.json
out=GPT_SoVITS/pretrained_models/chinese-hubert-base/preprocessor_config.json
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-hubert-base/pytorch_model.bin
out=GPT_SoVITS/pretrained_models/chinese-hubert-base/pytorch_model.bin
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-roberta-wwm-ext-large/config.json
out=GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/config.json
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-roberta-wwm-ext-large/pytorch_model.bin
out=GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/pytorch_model.bin
https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-roberta-wwm-ext-large/tokenizer.json
out=GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/tokenizer.json
# UVR5
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2_all_vocals.pth
out=tools/uvr5/uvr5_weights/HP2_all_vocals.pth
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP3_all_vocals.pth
out=tools/uvr5/uvr5_weights/HP3_all_vocals.pth
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5_only_main_vocal.pth
out=tools/uvr5/uvr5_weights/HP5_only_main_vocal.pth
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoAggressive.pth
out=tools/uvr5/uvr5_weights/VR-DeEchoAggressive.pth
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoDeReverb.pth
out=tools/uvr5/uvr5_weights/VR-DeEchoDeReverb.pth
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoNormal.pth
out=tools/uvr5/uvr5_weights/VR-DeEchoNormal.pth
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx
out=tools/uvr5/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx

46
Dockerfile Normal file
View File

@ -0,0 +1,46 @@
# Base CUDA image
FROM cnstark/pytorch:2.0.1-py3.9.17-cuda11.8.0-ubuntu20.04
# Install 3rd party apps
ENV DEBIAN_FRONTEND=noninteractive
ENV TZ=Etc/UTC
RUN apt-get update && \
apt-get install -y --no-install-recommends tzdata ffmpeg libsox-dev parallel aria2 git git-lfs && \
rm -rf /var/lib/apt/lists/* && \
git lfs install
# Install python packages
WORKDIR /temp
COPY ./requirements.txt /temp/requirements.txt
RUN pip install --no-cache-dir -r requirements.txt
# Copy application
WORKDIR /workspace
COPY . /workspace
# Download models
RUN chmod +x /workspace/Docker/download.sh && /workspace/Docker/download.sh
# Clone 3rd repos
WORKDIR /workspace/tools/damo_asr/models
RUN git clone --depth 1 https://www.modelscope.cn/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch && \
(cd speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch && git lfs pull)
RUN git clone --depth 1 https://www.modelscope.cn/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch.git speech_fsmn_vad_zh-cn-16k-common-pytorch && \
(cd speech_fsmn_vad_zh-cn-16k-common-pytorch && git lfs pull)
RUN git clone --depth 1 https://www.modelscope.cn/iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch.git punc_ct-transformer_zh-cn-common-vocab272727-pytorch && \
(cd punc_ct-transformer_zh-cn-common-vocab272727-pytorch && git lfs pull)
RUN parallel --will-cite -a /workspace/Docker/damo.sha256 "echo -n {} | sha256sum -c"
WORKDIR /workspace
EXPOSE 9870
EXPOSE 9871
EXPOSE 9872
EXPOSE 9873
EXPOSE 9874
CMD ["python", "webui.py"]