Dockerfile

@@ -20,7 +20,7 @@ ENV PATH="$HOME/miniconda/bin:$PATH"
 RUN conda init
 RUN conda install python=$PYTHON_VERSION
 RUN python3 -m pip install --upgrade pip
-RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+RUN pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
 
 RUN mkdir $HOME/ai-voice-cloning
 WORKDIR $HOME/ai-voice-cloning

README.md

@@ -1,6 +1,6 @@
 # AI Voice Cloning
 
-> **Note** This project is effectively abandonware due to requiring a rewrite. Please use [JarodMica/ai-voice-cloning](https://github.com/JarodMica/ai-voice-cloning).
+> **Note** This project has been in dire need of being rewritten from the ground up for some time. Apologies for any crust from my rather spaghetti code.
 
 This [repo](https://git.ecker.tech/mrq/ai-voice-cloning)/[rentry](https://rentry.org/AI-Voice-Cloning/) aims to serve as both a foolproof guide for setting up AI voice cloning tools for legitimate, local use on Windows/Linux, as well as a stepping stone for anons that genuinely want to play around with [TorToiSe](https://github.com/neonbjb/tortoise-tts).
 
@@ -16,4 +16,4 @@ Please consult [the wiki](https://git.ecker.tech/mrq/ai-voice-cloning/wiki) for
 
 ## Bug Reporting
 
-If you run into any problems, please refer to the [issues you may encounter](https://git.ecker.tech/mrq/ai-voice-cloning/wiki/Issues) wiki page first.
+If you run into any problems, please refer to the [issues you may encounter](https://git.ecker.tech/mrq/ai-voice-cloning/wiki/Issues) wiki page first.

modules/tortoise-tts

@@ -1 +1 @@
-Subproject commit bf3b6c87aa825295f64a31d010fd5e896fbcda43
+Subproject commit b10c58436d6871c26485d30b203e6cfdd4167602

notebook_colab.ipynb

@@ -38,24 +38,10 @@
             
          ],
          "source":[
-            "!apt install python3.10-venv\n",
+            "!apt install python3.8-venv\n",
             "!git clone https://git.ecker.tech/mrq/ai-voice-cloning/\n",
             "%cd /content/ai-voice-cloning\n",
-            "# get local dependencies\n",
-            "!git submodule init\n",
-            "!git submodule update --remote\n",
-            "# setup venv\n",
-            "!python3 -m venv venv\n",
-            "!source ./venv/bin/activate\n",
-            "!python3 -m pip install --upgrade pip # just to be safe\n",
-            "# CUDA\n",
-            "!pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n",
-            "# install requirements\n",
-            "!python3 -m pip install -r ./modules/tortoise-tts/requirements.txt # install TorToiSe requirements\n",
-            "!python3 -m pip install -e ./modules/tortoise-tts/ # install TorToiSe\n",
-            "!python3 -m pip install -r ./modules/dlas/requirements.txt # instal DLAS requirements, last, because whisperx will break a dependency here\n",
-            "!python3 -m pip install -e ./modules/dlas/ # install DLAS\n",
-            "!python3 -m pip install -r ./requirements.txt # install local requirements"
+            "!./setup-cuda.sh"
          ]
       },
       {
@@ -129,8 +115,7 @@
          "cell_type":"code",
          "source":[
             "%cd /content/ai-voice-cloning/\n",
-            "!source ./venv/bin/activate\n",
-            "!python3 ./src/main.py --share"
+            "!./start.sh --share"
          ],
          "metadata":{
             "id":"QRA8jF3cF-YJ"

requirements.txt

@@ -1,9 +1,5 @@
---extra-index-url https://download.pytorch.org/whl/cu118
-torch>=2.1.0
-torchvision
-torchaudio
+git+https://github.com/openai/whisper.git
 
-openai-whisper
 more-itertools
 ffmpeg-python
 gradio<=3.23.0
@@ -12,6 +8,4 @@ voicefixer
 psutil
 phonemizer
 pydantic==1.10.11
-websockets
-beartype==0.15.0
-pykakasi
+websockets

setup-cuda.bat

@@ -4,7 +4,7 @@ git submodule update --remote
 python -m venv venv
 call .\venv\Scripts\activate.bat
 python -m pip install --upgrade pip
-python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
 python -m pip install -r .\modules\tortoise-tts\requirements.txt
 python -m pip install -e .\modules\tortoise-tts\
 python -m pip install -r .\modules\dlas\requirements.txt

setup-cuda.sh

@@ -7,7 +7,7 @@ python3 -m venv venv
 source ./venv/bin/activate
 python3 -m pip install --upgrade pip # just to be safe
 # CUDA
-pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
 # install requirements
 python3 -m pip install -r ./modules/tortoise-tts/requirements.txt # install TorToiSe requirements
 python3 -m pip install -e ./modules/tortoise-tts/ # install TorToiSe

setup-rocm.sh

@@ -7,7 +7,7 @@ python3 -m venv venv
 source ./venv/bin/activate
 python3 -m pip install --upgrade pip # just to be safe
 # ROCM
-pip3 install torch==1.13.1 torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.2 # 5.4.2 doesn't work for me desu
+pip3 install torch==1.13.1 torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.2 # 5.4.2 doesn't work for me desu
 # install requirements
 python3 -m pip install -r ./modules/tortoise-tts/requirements.txt # install TorToiSe requirements
 python3 -m pip install -e ./modules/tortoise-tts/ # install TorToiSe