fix device=CPU usage if cuda is not available + improve code formating.

.gitignore

@@ -160,4 +160,5 @@ cython_debug/
 #.idea/
 
 base_models
-finetune_models
+finetune_models
+/test_model

Dockerfile

@@ -0,0 +1,20 @@
+FROM nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04
+
+RUN apt-get update && \
+    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common curl && \
+    add-apt-repository ppa:deadsnakes/ppa && \
+    apt-get update && \
+    DEBIAN_FRONTEND=noninteractive apt-get install -y python3.10 && \
+    curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
+
+# Copy the requirements.txt file to the container
+COPY requirements.txt /root/
+
+# Install the packages from requirements.txt
+RUN pip install --no-cache-dir -r /root/requirements.txt
+
+ENV GRADIO_SERVER_NAME=0.0.0.0
+
+WORKDIR /root/tts
+
+CMD ["/usr/bin/python3", "xtts_demo.py"]

docker-compose.yml

@@ -0,0 +1,28 @@
+version: '3.8'
+services:
+  tts_service:
+    build: .
+    image: tts_image
+    container_name: tts_container
+    command: ["/usr/bin/python3", "xtts_demo.py"]
+    volumes:
+      - .:/root/tts
+      - .cache:/root/.cache/huggingface # hugging face cache
+    ports:
+      - "5003:5003" # Map ports if your application uses them
+    #device_requests: # for futur docker version
+    #  - driver: nvidia
+    #    count: all
+    #    capabilities: [gpu]
+    stdin_open: true
+    tty: true
+    runtime: nvidia
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            # device_ids: ['0', '3']
+            capabilities: [gpu]
+
+# docker exec -it tts_container /bin/bash

install.bat

@@ -3,7 +3,7 @@
 python -m venv venv
 call venv/scripts/activate
 
-pip install torch==2.1.1+cu118 torchaudio==2.1.1+cu118 --index-url https://download.pytorch.org/whl/cu118
 pip install -r .\requirements.txt
+pip install torch==2.1.1+cu118 torchaudio==2.1.1+cu118 --index-url https://download.pytorch.org/whl/cu118
 
 python xtts_demo.py

install.mac.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+python -m venv venv
+source ./venv/bin/activate
+
+pip install -r requirements.txt
+pip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1
+
+python xtts_demo.py

pyproject.toml

@@ -0,0 +1,5 @@
+[tool.black]
+line-length = 100
+
+[tool.isort]
+profile = "black"

requirements.txt

@@ -1,6 +1,7 @@
-faster_whisper==0.10.0
-gradio==4.9.1
-tts == 0.22.0
+faster_whisper==1.0.2
+gradio==4.13.0
+spacy==3.7.4
+coqui-tts[languages] == 0.24.1
 
 cutlet
 fugashi[unidic-lite]