Dockerfile with uv. You can test with:

docker build . -t coqui
  mkdir output
  docker run -it -v ./output:/app/output coqui --text "Text for TTS" --out_path output/speech.wav

Dockerfile

@@ -1,19 +1,24 @@
 ARG BASE=nvidia/cuda:11.8.0-base-ubuntu22.04
-FROM ${BASE}
+FROM ${BASE} AS builder
 
-RUN apt-get update && apt-get upgrade -y
+WORKDIR /app
-RUN apt-get install -y --no-install-recommends gcc g++ make python3 python3-dev python3-pip python3-venv python3-wheel espeak-ng libsndfile1-dev && rm -rf /var/lib/apt/lists/*
+RUN apt update && apt upgrade -y && apt install -y curl build-essential libsndfile1-dev
-RUN pip3 install llvmlite --ignore-installed
 
-# Install Dependencies:
+# Install rustup
-RUN pip3 install torch torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
+RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
-RUN rm -rf /root/.cache/pip
+ENV PATH="/root/.cargo/bin:${PATH}"
 
-# Copy TTS repository contents:
+# Install uv
-WORKDIR /root
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
-COPY . /root
 
-RUN make install
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-dev
+ENV PATH="/app/.venv/bin:$PATH"
 
 ENTRYPOINT ["tts"]
 CMD ["--help"]

pyproject.toml

@@ -1,6 +1,68 @@
+[project]
+name = "coqui-tts"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.9, <3.10"
+dependencies = [
+    "pip",
+    "numpy==1.22.0",
+    "numba>=0.57.0",
+    "scipy>=1.11.2",
+    "torch>=2.1",
+    "torchaudio",
+    "soundfile>=0.12.0",
+    "librosa>=0.10.0",
+    "scikit-learn>=1.3.0",
+    "inflect>=5.6.0",
+    "tqdm>=4.64.1",
+    "anyascii>=0.3.0",
+    "pyyaml>=6.0",
+    "fsspec>=2023.6.0", # <= 2023.9.1 makes aux tests fail
+    "aiohttp>=3.8.1",
+    "packaging>=23.1",
+    "mutagen==1.47.0",
+    # deps for examples
+    "flask>=2.0.1",
+    # deps for inference
+    "pysbd>=0.3.4",
+    # deps for notebooks
+    "umap-learn>=0.5.1",
+    "pandas>=1.4,<2.0",
+    # deps for training
+    "matplotlib>=3.7.0",
+    # coqui stack
+    "trainer>=0.0.36",
+    # config management
+    "coqpit>=0.0.16",
+    # chinese g2p deps
+    "jieba",
+    "pypinyin",
+    # gruut+supported langs
+    "gruut[de,es,fr]==2.2.3",
+    # deps for korean
+    "hangul_romanize",
+    "jamo",
+    "nltk",
+    "g2pkk>=0.1.1",
+    # deps for bangla
+    "bangla",
+    "bnnumerizer",
+    "bnunicodenormalizer",
+    #deps for tortoise
+    "einops>=0.6.0",
+    "transformers>=4.33.0",
+    #deps for bark
+    "encodec>=0.1.1",
+    # deps for XTTS
+    "unidecode>=1.3.2",
+    "num2words",
+    "spacy[ja]>=3"
+]
+
 [build-system]
 requires = [
-    "setuptools",
+    "setuptools<69.0.0",
     "wheel",
     "cython~=0.29.30",
     "numpy>=1.22.0",
@@ -18,3 +80,4 @@ target-version = ['py39']
 line_length = 120
 profile = "black"
 multi_line_output = 3
+