0

ChatTTS/Dockerfile.cpu

@@ -0,0 +1,7 @@
+FROM pytorch/torchserve:0.11.0-cpu as builder
+
+WORKDIR /app
+
+COPY . ./
+
+RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

ChatTTS/README.md

@@ -0,0 +1,10 @@
+# ChatTTS
+
+文本转语音
+
+
+
+
+
+[2noise/ChatTTS: A generative speech model for daily dialogue.](https://github.com/2noise/ChatTTS)
+

ChatTTS/docker-compose.cpu.yaml

@@ -0,0 +1,16 @@
+services:
+  chat-tts-ui:
+    build:
+      context: .
+      dockerfile: Dockerfile.cpu
+    container_name: chat-tts-ui
+    restart: always
+    volumes:
+      - "./:/app"
+    ports:
+      - 9966:9966
+    user: "${UID}:${GID}"
+    environment:
+      LOG_LEVEL: DEBUG
+      WEB_ADDRESS: 0.0.0.0:9966
+    command: python3 app.py

README.md

@@ -1,2 +1,57 @@
 # TTS
 
+文字转语音，语音clone
+
+
+
+## XTTS
+
+
+
+## VoiceCraft2
+
+语音编辑和零样本文本转语音（TTS），包括有声书、互联网视频和播客。VoiceCraft只需要几秒钟的参考语音就能克隆声音。
+
+<https://github.dev/jasonppy/VoiceCraft>
+
+
+
+## ChatTTS
+
+<https://github.com/2noise/ChatTTS>
+
+[2Noise/ChatTTS · Hugging Face](https://huggingface.co/2Noise/ChatTTS)
+
+
+
+## TTS
+
+
+
+ <https://github.com/coqui-ai/TTS>
+
+
+
+## GPT-SoVITS
+
+
+
+[RVC-Boss/GPT-SoVITS: 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)](https://github.com/RVC-Boss/GPT-SoVITS)
+
+
+
+[GPT-SoVITS · Studios](https://www.modelscope.cn/studios/xzjosh/GPT-SoVITS/)
+
+
+
+
+
+## Reference
+
+
+
+https://fish.audio/zh-CN/
+
+
+
+[ChatTTS: Text-to-Speech For Chat](https://chattts.com/)

VoiceCraft/README.md

@@ -0,0 +1,67 @@
+# VoiceCraft
+语音编辑和零样本文本转语音（TTS），包括有声书、互联网视频和播客。VoiceCraft只需要几秒钟的参考语音就能克隆声音。
+
+## Usage
+
+项目：
+https://github.com/jasonppy/VoiceCraft
+
+模型：
+https://huggingface.co/pyp1/VoiceCraft/tree/main
+
+演示页面:
+https://jasonppy.github.io/VoiceCraft_web/
+
+```
+conda create -n voicecraft python=3.9.16
+conda activate voicecraft
+
+pip install -e git+https://github.com/facebookresearch/audiocraft.git@c5157b5bf14bf83449c17ea1eeb66c19fb4bc7f0#egg=audiocraft
+pip install xformers==0.0.22
+pip install torchaudio==2.0.2 torch==2.0.1 # this assumes your system is compatible with CUDA 11.7, otherwise checkout https://pytorch.org/get-started/previous-versions/#v201
+apt-get install ffmpeg # if you don't already have ffmpeg installed
+apt-get install espeak-ng # backend for the phonemizer installed below
+pip install tensorboard==2.16.2
+pip install phonemizer==3.2.1
+pip install datasets==2.16.0
+pip install torchmetrics==0.11.1
+# install MFA for getting forced-alignment, this could take a few minutes
+conda install -c conda-forge montreal-forced-aligner=2.2.17 openfst=1.8.2 kaldi=5.5.1068
+# conda install pocl # above gives an warning for installing pocl, not sure if really need this
+
+# to run ipynb
+conda install -n voicecraft ipykernel --no-deps --force-reinstall
+
+
+
+# 1. clone the repo on in a directory on a drive with plenty of free space
+git clone git@github.com:jasonppy/VoiceCraft.git
+cd VoiceCraft
+
+# 2. assumes you have docker installed with nvidia container container-toolkit (windows has this built into the driver)
+# https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/1.13.5/install-guide.html
+# sudo apt-get install -y nvidia-container-toolkit-base || yay -Syu nvidia-container-toolkit || echo etc...
+
+# 3. Try to start an existing container otherwise create a new one passing in all GPUs
+./start-jupyter.sh  # linux
+start-jupyter.bat   # windows
+
+# 4. now open a webpage on the host box to the URL shown at the bottom of:
+docker logs jupyter
+
+# 5. optionally look inside from another terminal
+docker exec -it jupyter /bin/bash
+export USER=(your_linux_username_used_above)
+export HOME=/home/$USER
+sudo apt-get update
+
+# 6. confirm video card(s) are visible inside container
+nvidia-smi
+
+# 7. Now in browser, open inference_tts.ipynb and work through one cell at a time
+echo GOOD LUCK
+```
+
+推理和训练：
+
+查看inference_speech_editing.ipynb和inference_tts.ipynb。