Docker image

Dockerfile

@@ -0,0 +1,33 @@
+FROM nvidia/cuda:11.3.1-base-ubuntu20.04
+
+ENV PYTHON_VERSION=3.8
+
+RUN export DEBIAN_FRONTEND=noninteractive \
+    && apt-get -qq update \
+    && apt-get -qq install --no-install-recommends \
+    libsndfile1-dev \
+    git \
+    python${PYTHON_VERSION} \
+    python${PYTHON_VERSION}-venv \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN ln -s -f /usr/bin/python${PYTHON_VERSION} /usr/bin/python3 && \
+    ln -s -f /usr/bin/python${PYTHON_VERSION} /usr/bin/python && \
+    ln -s -f /usr/bin/pip3 /usr/bin/pip
+
+RUN pip install --upgrade pip
+
+# 2. Copy files
+COPY . /src
+
+RUN pip install torch==1.12.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
+
+WORKDIR /src
+# 3. Install dependencies
+RUN pip install -r requirements-docker.txt
+
+RUN python3 setup.py install
+
+
+

Dockerfile.moderngpu

@@ -0,0 +1,31 @@
+
+FROM nvidia/cuda:11.8.0-base-ubuntu20.04
+
+ENV PYTHON_VERSION=3.8
+
+RUN export DEBIAN_FRONTEND=noninteractive \
+    && apt-get -qq update \
+    && apt-get -qq install --no-install-recommends \
+    libsndfile1-dev \
+    git \
+    python${PYTHON_VERSION} \
+    python${PYTHON_VERSION}-venv \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN ln -s -f /usr/bin/python${PYTHON_VERSION} /usr/bin/python3 && \
+    ln -s -f /usr/bin/python${PYTHON_VERSION} /usr/bin/python && \
+    ln -s -f /usr/bin/pip3 /usr/bin/pip
+
+RUN pip install --upgrade pip
+
+# 2. Copy files
+COPY . /src
+
+RUN pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
+
+WORKDIR /src
+# 3. Install dependencies
+RUN pip install -r requirements-docker.txt
+
+RUN python3 setup.py install

README.md

@@ -213,6 +213,18 @@ good clips:
 5. Try to find clips that are spoken in such a way as you wish your output to sound like. For example, if you want to hear your target voice read an audiobook, try to find clips of them reading a book.
 6. The text being spoken in the clips does not matter, but diverse text does seem to perform better.
 
+### Using it with Docker
+To use Gpu with Docker [install the appropriate drivers and the NVIDIA Container Runtime](https://docs.docker.com/config/containers/resource_constraints/#gpu). 
+If you have a modern GPU like RTX 4090 you can build yout docker image using Dockerfile.moderngpu file. 
+If you have an older GPU like K80 or V100 you can use the other Dockerfile .
+Download models and put them in a models folder, create an empty transformers folder to serve as download cache for huggingface transformers.
+Mount it as a volume in your container
+It's also useful to mount another volume for the outputs so create an outputs folder too
+
+```shell
+ docker run -v models:/src/models outputs:/outputs  -e "TORTOISE_MODELS_DIR=/src/models" -e "TRANSFORMERS_CACHE=/src/models/transformers"  --rm --gpus all tortoise_tts:latest python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast --output_path /outputs
+```
+
 ## Advanced Usage
 
 ### Generation settings

requirements-docker.txt

@@ -0,0 +1,15 @@
+tqdm
+rotary_embedding_torch
+transformers==4.19
+tokenizers
+inflect
+progressbar
+einops
+unidecode
+scipy
+librosa
+numpy==1.20.0
+numba==0.48.0
+threadpoolctl
+llvmlite
+appdirs