updated dockerfile withh entrypoint

.gitignore

@@ -1,3 +1,6 @@
+# data
+data/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

Dockerfile

@@ -45,3 +45,6 @@ RUN bash -c "source ${CONDA_DIR}/etc/profile.d/conda.sh && conda activate tortoi
 
 # Default command
 CMD ["/bin/bash"]
+
+# Default entrypoint
+ENTRYPOINT ["python", "tortoise/do_tts.py"]

bin/docker-build.sh

@@ -0,0 +1 @@
+docker build . -t tts

bin/docker-remove.sh

@@ -0,0 +1,9 @@
+# optionally: --gpus all 
+docker run \ 
+  -e TORTOISE_MODELS_DIR=/models \
+  -v ./data/models:/models \
+  -v ./data/results:/results \
+  -v ./data/.cache/huggingface:/root/.cache/huggingface \
+  -v /root:/work \
+  --name tts-app \
+  -it tts

bin/docker-run.sh

@@ -0,0 +1,8 @@
+docker run --gpus all \
+  -e TORTOISE_MODELS_DIR=/models \
+  -v ./data/models:/models \
+  -v ./data/results:/results \
+  -v ./data/.cache/huggingface:/root/.cache/huggingface \
+  -v /root:/work \
+  --name tts-app \
+  -it tts

bin/docker-start.sh

@@ -0,0 +1,2 @@
+. bin/docker-build.sh
+. bin/docker-run.sh

tortoise/do_tts.py

@@ -10,8 +10,9 @@ from utils.audio import load_voices
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('--text', type=str, help='Text to speak.', default="The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.")
-    parser.add_argument('--voice', type=str, help='Selects the voice to use for generation. See options in voices/ directory (and add your own!) '
-                                                 'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='random')
+    parser.add_argument('--voice', type=str, help="""
+        Selects the voice to use for generation. See options in voices/ directory (and add your own!) '
+        'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.""", default='random')
     parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='fast')
     parser.add_argument('--use_deepspeed', type=str, help='Use deepspeed for speed bump.', default=False)
     parser.add_argument('--kv_cache', type=bool, help='If you disable this please wait for a long a time to get the output', default=True)