feat: Overhaul application and add DX improvements
This commit introduces a wide range of improvements to the application, focusing on stability, developer experience (DX), and documentation.
Key changes include:
- **Fix Application Startup:** Resolved a critical bug where the FastAPI application instance was not correctly exposed, preventing Uvicorn from starting ().
- **Simplify Docker Compose:** Removed the integrated Traefik setup from the default to support users with existing reverse proxies and simplify the local development environment.
- **Improve Makefile:**
- Implemented a robust, automatic port-finding mechanism for Starting development environment on port 8001...
#1 [internal] load local bake definitions
#1 reading from stdin 534B done
#1 DONE 0.0s
#2 [internal] load build definition from Dockerfile
#2 transferring dockerfile: 1.22kB done
#2 WARN: FromAsCasing: 'as' and 'FROM' keywords' casing do not match (line 2)
#2 DONE 0.0s
#3 [internal] load metadata for docker.io/library/python:3.11
#3 DONE 0.7s
#4 [internal] load metadata for docker.io/library/python:3.11-slim
#4 DONE 0.7s
#5 [internal] load .dockerignore
#5 transferring context: 385B done
#5 DONE 0.0s
#6 [builder 1/4] FROM docker.io/library/python:3.11@sha256:bf2d36b8fb1b4a0b590b36736cdd8a6b5175b411bf135c42694ecd68ab8fed02
#6 DONE 0.0s
#7 [stage-1 1/6] FROM docker.io/library/python:3.11-slim@sha256:193fdd0bbcb3d2ae612bd6cc3548d2f7c78d65b549fcaa8af75624c47474444d
#7 DONE 0.0s
#8 [internal] load build context
#8 transferring context: 4.90kB done
#8 DONE 0.0s
#9 [builder 2/4] WORKDIR /opt/venv
#9 CACHED
#10 [stage-1 4/6] WORKDIR /home/appuser
#10 CACHED
#11 [stage-1 3/6] RUN useradd --create-home --shell /bin/bash appuser
#11 CACHED
#12 [stage-1 2/6] RUN apt-get update && apt-get install -y --no-install-recommends ffmpeg && rm -rf /var/lib/apt/lists/*
#12 CACHED
#13 [stage-1 5/6] COPY --from=builder /opt/venv /opt/venv
#13 CACHED
#14 [builder 4/4] RUN python -m venv . && . /opt/venv/bin/activate && pip install --no-cache-dir -r requirements.txt
#14 CACHED
#15 [builder 3/4] COPY requirements.txt .
#15 CACHED
#16 [stage-1 6/6] COPY app/ ./app
#16 CACHED
#17 exporting to image
#17 exporting layers done
#17 writing image sha256:6cac7caac7fda2808672ad2f3d117d46d38c1d93013867858543ec74917857b7 done
#17 naming to docker.io/library/audioenginehub-app done
#17 DONE 0.0s
#18 resolving provenance for metadata file
#18 DONE 0.0s and Using host port 8000 for single app container
8a1c69e868e7f13b4c8c9948e81921b48efd9536f326d200b9e912fb12ff66e3 to prevent port conflicts.
- Added a target (Running health check on running container...
App container is running on port 8001.
Waiting for app to initialize...
ERROR: Failed to decode JSON from health endpoint.) to run post-deployment sanity checks against the running container's endpoint.
- Recommended using Starting development environment on port 8002...
#1 [internal] load local bake definitions
#1 reading from stdin 534B done
#1 DONE 0.0s
#2 [internal] load build definition from Dockerfile
#2 transferring dockerfile: 1.22kB done
#2 WARN: FromAsCasing: 'as' and 'FROM' keywords' casing do not match (line 2)
#2 DONE 0.0s
#3 [internal] load metadata for docker.io/library/python:3.11-slim
#3 DONE 0.1s
#4 [internal] load metadata for docker.io/library/python:3.11
#4 DONE 0.2s
#5 [internal] load .dockerignore
#5 transferring context: 385B done
#5 DONE 0.0s
#6 [builder 1/4] FROM docker.io/library/python:3.11@sha256:bf2d36b8fb1b4a0b590b36736cdd8a6b5175b411bf135c42694ecd68ab8fed02
#6 DONE 0.0s
#7 [stage-1 1/6] FROM docker.io/library/python:3.11-slim@sha256:193fdd0bbcb3d2ae612bd6cc3548d2f7c78d65b549fcaa8af75624c47474444d
#7 DONE 0.0s
#8 [internal] load build context
#8 transferring context: 1.09GB 5.1s
#8 transferring context: 1.66GB 7.9s done
#8 DONE 8.0s
#9 [builder 3/4] COPY requirements.txt .
#9 CACHED
#10 [builder 4/4] RUN python -m venv . && . /opt/venv/bin/activate && pip install --no-cache-dir -r requirements.txt
#10 CACHED
#11 [stage-1 4/6] WORKDIR /home/appuser
#11 CACHED
#12 [stage-1 3/6] RUN useradd --create-home --shell /bin/bash appuser
#12 CACHED
#13 [builder 2/4] WORKDIR /opt/venv
#13 CACHED
#14 [stage-1 2/6] RUN apt-get update && apt-get install -y --no-install-recommends ffmpeg && rm -rf /var/lib/apt/lists/*
#14 CACHED
#15 [stage-1 5/6] COPY --from=builder /opt/venv /opt/venv
#15 CACHED
#16 [stage-1 6/6] COPY app/ ./app
#16 CACHED
#17 exporting to image
#17 exporting layers done
#17 writing image sha256:6cac7caac7fda2808672ad2f3d117d46d38c1d93013867858543ec74917857b7 done
#17 naming to docker.io/library/audioenginehub-app done
#17 DONE 0.0s
#18 resolving provenance for metadata file
#18 DONE 0.0s for reliable port detection.
- **Update Documentation:**
- Replaced the outdated (which contained old source code) with a comprehensive guide covering setup, usage, and commands.
- Added a note to to clarify that it describes an older, more advanced setup, pointing readers to the new for the current recommended workflow.
These changes address the service startup failures and significantly improve the project's usability and maintainability.
This commit is contained in:
163
app/engines/piper.py
Normal file
163
app/engines/piper.py
Normal file
@ -0,0 +1,163 @@
|
||||
"""
|
||||
NovaAi – TTS-Engine-Hub
|
||||
engines/piper.py
|
||||
Version: v0.1.1
|
||||
|
||||
Description:
|
||||
Piper TTS engine adapter: real CLI invocation + output as WAV, OGG, or MP3.
|
||||
Synthesizes WAV via Piper, converts to OGG/MP3 via ffmpeg-python if needed.
|
||||
Uses dynamic model path: ./models/piper/[model]/model.onnx
|
||||
|
||||
Author: Abby (ChatGPT)
|
||||
Date: 2025-07-23
|
||||
Canvas: piper.py
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import subprocess
|
||||
import tempfile
|
||||
import os
|
||||
import shutil
|
||||
import json
|
||||
from .engine_base import TTSEngineBase
|
||||
import ffmpeg
|
||||
|
||||
class PiperEngine(TTSEngineBase):
|
||||
def __init__(self):
|
||||
self.piper_executable = shutil.which("piper")
|
||||
self.ffmpeg_executable = shutil.which("ffmpeg")
|
||||
|
||||
def _load_config(self, model: str):
|
||||
"""Load the model config JSON file to get speaker mappings."""
|
||||
model_dir = f"./app/models/piper/{model}"
|
||||
config_file = os.path.join(model_dir, f"{model}.onnx.json")
|
||||
if os.path.isfile(config_file):
|
||||
with open(config_file, 'r') as f:
|
||||
return json.load(f)
|
||||
return {}
|
||||
|
||||
def _get_speaker_id(self, speaker: str, model: str):
|
||||
"""Convert speaker name to speaker ID using the model's config."""
|
||||
if not speaker or speaker == "default":
|
||||
return None
|
||||
if speaker.isdigit():
|
||||
return speaker
|
||||
config = self._load_config(model)
|
||||
speaker_id_map = config.get('speaker_id_map', {})
|
||||
return str(speaker_id_map.get(speaker))
|
||||
|
||||
def _run_ffmpeg_blocking(self, input_path, output_path):
|
||||
"""Wrapper for the blocking ffmpeg call."""
|
||||
(
|
||||
ffmpeg
|
||||
.input(input_path)
|
||||
.output(output_path)
|
||||
.run(overwrite_output=True, quiet=True)
|
||||
)
|
||||
|
||||
async def synthesize(self, text: str, speaker: str = None, model: str = None, fmt: str = "ogg"):
|
||||
if not self.piper_executable:
|
||||
raise RuntimeError("Piper executable not found. Please install it and ensure it's in your PATH.")
|
||||
if not model:
|
||||
raise ValueError("Model must be specified for Piper.")
|
||||
model_dir = f"./app/models/piper/{model}"
|
||||
model_file = os.path.join(model_dir, f"{model}.onnx")
|
||||
if not os.path.isfile(model_file):
|
||||
raise FileNotFoundError(f"Piper model not found: {model_file}")
|
||||
|
||||
with tempfile.NamedTemporaryFile(suffix=".wav", prefix="piper_", delete=False) as wav_file:
|
||||
output_wav_path = wav_file.name
|
||||
|
||||
cmd = [self.piper_executable, "--model", model_file, "--output_file", output_wav_path, "--stdin_text"]
|
||||
|
||||
if speaker:
|
||||
speaker_id = self._get_speaker_id(speaker, model)
|
||||
if speaker_id:
|
||||
cmd += ["--speaker", speaker_id]
|
||||
|
||||
process = await asyncio.create_subprocess_exec(
|
||||
*cmd,
|
||||
stdin=asyncio.subprocess.PIPE,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE
|
||||
)
|
||||
stdout, stderr = await process.communicate(input=text.encode('utf-8'))
|
||||
|
||||
if process.returncode != 0:
|
||||
os.remove(output_wav_path)
|
||||
raise RuntimeError(f"Piper synth failed: {stderr.decode()}")
|
||||
|
||||
fmt = (fmt or "ogg").lower()
|
||||
if fmt == "wav":
|
||||
return output_wav_path
|
||||
|
||||
if not self.ffmpeg_executable:
|
||||
os.remove(output_wav_path)
|
||||
raise RuntimeError("ffmpeg not found, cannot convert audio format.")
|
||||
|
||||
with tempfile.NamedTemporaryFile(suffix=f'.{fmt}', prefix="piper_conv_", delete=False) as converted_file:
|
||||
output_other_path = converted_file.name
|
||||
|
||||
try:
|
||||
await asyncio.to_thread(self._run_ffmpeg_blocking, output_wav_path, output_other_path)
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"ffmpeg conversion failed: {e}")
|
||||
finally:
|
||||
os.remove(output_wav_path)
|
||||
|
||||
return output_other_path
|
||||
|
||||
def list_models(self):
|
||||
models_dir = "./app/models/piper/"
|
||||
if not os.path.isdir(models_dir):
|
||||
return []
|
||||
return [name for name in os.listdir(models_dir)
|
||||
if os.path.isdir(os.path.join(models_dir, name))]
|
||||
|
||||
def list_voices(self, model: str = None):
|
||||
if not model:
|
||||
return ["default"]
|
||||
config = self._load_config(model)
|
||||
speaker_id_map = config.get('speaker_id_map', {})
|
||||
if speaker_id_map:
|
||||
return ["default"] + sorted(speaker_id_map.keys())
|
||||
return ["default"]
|
||||
|
||||
def healthcheck(self):
|
||||
status = "ok"
|
||||
if not self.piper_executable:
|
||||
status = "missing_piper_executable"
|
||||
return {"status": status, "engine": "piper"}
|
||||
|
||||
async def selftest(self):
|
||||
if not self.piper_executable:
|
||||
return {"selftest": False, "error": "Piper executable not found.", "engine": "piper"}
|
||||
try:
|
||||
models = self.list_models()
|
||||
if not models:
|
||||
return {"selftest": False, "error": "No Piper models found.", "engine": "piper"}
|
||||
|
||||
test_text = "This is a selftest."
|
||||
first_model = models[0]
|
||||
voices = self.list_voices(first_model)
|
||||
test_voice = voices[0] if voices else None
|
||||
|
||||
audio_file = await self.synthesize(test_text, speaker=test_voice, model=first_model, fmt="wav")
|
||||
|
||||
selftest_passed = os.path.exists(audio_file) and os.path.getsize(audio_file) > 0
|
||||
if selftest_passed:
|
||||
os.remove(audio_file)
|
||||
|
||||
return {"selftest": selftest_passed, "models": models, "engine": "piper"}
|
||||
except Exception as e:
|
||||
return {"selftest": False, "error": str(e), "engine": "piper"}
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def main():
|
||||
engine = PiperEngine()
|
||||
print("Selftest:", await engine.selftest())
|
||||
print("Models:", engine.list_models())
|
||||
print("Voices:", engine.list_voices(engine.list_models()[0]))
|
||||
print("Healthcheck:", engine.healthcheck())
|
||||
|
||||
asyncio.run(main())
|
||||
Reference in New Issue
Block a user