stephan/audio-engine-hub
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Overhaul application and add DX improvements

Browse Source 
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:
Stephan Wilkens
2025-12-04 17:33:44 +01:00
parent 21cdc65ade
commit 528a185d3b
32 changed files with 277 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
app/config.py Normal file
View File

@ -0,0 +1,25 @@
"""
NovaAi – TTS-Engine-Hub
config.py
Version: v0.0.1
Description:
Centralized configuration management using pydantic-settings.
Loads settings from a .env file and environment variables.
"""
from pydantic_settings import BaseSettings, SettingsConfigDict
from typing import List, Set
class Settings(BaseSettings):
# Server Configuration
HOST: str = "0.0.0.0"
PORT: int = 8000
# Application Configuration
ACTIVE_ENGINES: Set[str] = {"piper"}
ASSET_DIR: str = "/home/appuser/app/asset"
AUDIO_CACHE_DIR: str = "/home/appuser/app/asset/audio"
model_config = SettingsConfigDict(env_file=".env", env_file_encoding='utf-8')
settings = Settings()

48
app/engines/chattts.py Normal file
View File

@ -0,0 +1,48 @@
"""
NovaAi – TTS-Engine-Hub
engines/chattts.py
Version: v0.0.1
Description:
ChatTTS engine adapter.
Implements TTSEngineBase interface for ChatTTS integration (dummy implementation).
Author: Abby (ChatGPT)
Date: 2025-07-23
Canvas: chattts.py
"""
import asyncio
from .engine_base import TTSEngineBase
class ChatTTSEngine(TTSEngineBase):
async def synthesize(self, text: str, speaker: str = None, model: str = None, fmt: str = "mp3"):
# Dummy implementation: returns an empty string as it doesn't produce a file.
print("Warning: ChatTTSEngine.synthesize is a dummy and does not produce audio.")
return ""
def list_models(self):
# Dummy implementation
return ["chattts-v1", "chattts-v2"]
def list_voices(self, model: str = None):
# Dummy implementation
return ["default", "custom1", "custom2"]
def healthcheck(self):
# Dummy implementation
return {"status": "ok", "engine": "chattts"}
async def selftest(self):
# Dummy implementation
return {"selftest": True, "engine": "chattts"}
if __name__ == "__main__":
async def main():
engine = ChatTTSEngine()
print("Selftest:", await engine.selftest())
print("Models:", engine.list_models())
print("Voices:", engine.list_voices())
print("Healthcheck:", engine.healthcheck())
asyncio.run(main())

45
app/engines/engine_base.py Normal file
View File

@ -0,0 +1,45 @@
"""
NovaAi – TTS-Engine-Hub
engine_base.py
Version: v0.0.1
Description:
Abstract base class for all TTS engine modules.
Defines the required interface for engine adapters.
Author: Abby (ChatGPT)
Date: 2025-07-23
Canvas: engine_base.py
"""
from abc import ABC, abstractmethod
import asyncio
class TTSEngineBase(ABC):
@abstractmethod
async def synthesize(self, text: str, speaker: str = None, model: str = None, fmt: str = "ogg"):
"""
Asynchronously generate speech audio from text input.
Returns path to audio file.
"""
raise NotImplementedError
@abstractmethod
def list_models(self):
"""Return a list of available models."""
raise NotImplementedError
@abstractmethod
def list_voices(self, model: str = None):
"""Return a list of available voices for a model."""
raise NotImplementedError
@abstractmethod
def healthcheck(self):
"""Return health/status info for this engine."""
raise NotImplementedError
@abstractmethod
async def selftest(self):
"""Asynchronously run internal self-test (basic functionality check)."""
raise NotImplementedError

1
app/engines/f5-tts-voices/default.txt Normal file
View File

@ -0,0 +1 @@
Some call me nature, others call me mother nature.

143
app/engines/f5_tts.py Normal file
View File

@ -0,0 +1,143 @@
"""
NovaAi – TTS-Engine-Hub
f5_tts.py
Version: v0.0.2
Description:
F5-TTS engine module.
Implements the TTSEngineBase for F5-TTS text-to-speech synthesis.
Now with robust speaker handling.
Author: Your Name (or leave as generated)
Date: 2025-12-03
"""
import os
import tempfile
import torch
import torchaudio
import numpy as np
import soundfile as sf
import asyncio
from .engine_base import TTSEngineBase
from importlib.resources import files
try:
from f5_tts.api import F5TTS
except ImportError:
print("Warning: F5TTS could not be imported. F5-TTS engine will not be available.")
F5TTS = None
class F5TTSEngine(TTSEngineBase):
def __init__(self):
# Initialize F5-TTS specific resources, models, etc.
print("F5-TTS Engine Initializing...")
self.speakers = {}
self.model = None
if F5TTS:
try:
self.model = F5TTS(model="F5TTS_v1_Base")
print("F5-TTS Engine Initialized.")
self._load_speakers()
except Exception as e:
print(f"Error initializing F5-TTS Engine: {e}")
self.model = None
else:
print("F5-TTS Engine not initialized because F5TTS is not available.")
def _load_speakers(self):
# Add the default speaker
default_wav = str(files("f5_tts").joinpath("infer/examples/basic/basic_ref_en.wav"))
default_txt = "app/models/f5-tts-voices/default.txt"
if os.path.exists(default_txt):
self.speakers["default"] = {"wav": default_wav, "txt": default_txt}
# Scan for custom speakers
voices_dir = "app/models/f5-tts-voices"
if not os.path.isdir(voices_dir):
return
for file in os.listdir(voices_dir):
if file.endswith(".wav"):
speaker_name = file.rsplit('.', 1)[0]
wav_path = os.path.join(voices_dir, file)
txt_path = os.path.join(voices_dir, f"{speaker_name}.txt")
if os.path.exists(txt_path):
self.speakers[speaker_name] = {"wav": wav_path, "txt": txt_path}
print(f"Found custom speaker: {speaker_name}")
def _blocking_synthesize(self, text: str, speaker: str, fmt: str):
"""The actual blocking synthesis logic."""
speaker_data = self.speakers[speaker]
ref_file = speaker_data["wav"]
with open(speaker_data["txt"], 'r') as f:
ref_text = f.read()
print(f"F5-TTS: Synthesizing '{text}' with reference voice from '{ref_file}'.")
wav, sr, spec = self.model.infer(
ref_file=ref_file,
ref_text=ref_text,
gen_text=text,
)
with tempfile.NamedTemporaryFile(delete=False, suffix=f".{fmt}") as temp_file:
if fmt == "wav":
torchaudio.save(temp_file.name, torch.from_numpy(wav).unsqueeze(0), sr, format="wav")
else:
# Convert to float32 for soundfile
wav_float = wav.astype(np.float32) / np.iinfo(wav.dtype).max
sf.write(temp_file.name, wav_float, sr)
return temp_file.name
async def synthesize(self, text: str, speaker: str = None, model: str = None, fmt: str = "ogg"):
"""
Asynchronously generate speech audio from text input using F5-TTS.
"""
if not self.model:
raise RuntimeError("F5-TTS Engine not initialized.")
speaker_to_use = speaker if speaker in self.speakers else "default"
if speaker and speaker not in self.speakers:
print(f"Warning: Speaker '{speaker}' not found. Falling back to default speaker.")
if speaker_to_use not in self.speakers:
raise RuntimeError("No default speaker found for F5-TTS. Please add a 'default.wav' and 'default.txt' to the 'engines/f5-tts-voices' directory.")
try:
# Run the blocking synthesis in a separate thread
return await asyncio.to_thread(self._blocking_synthesize, text, speaker_to_use, fmt)
except Exception as e:
raise RuntimeError(f"F5-TTS synthesis failed: {e}")
def list_models(self):
"""Return a list of available F5-TTS models."""
if not self.model:
return []
return ["F5TTS_v1_Base"]
def list_voices(self, model: str = None):
"""Return a list of available F5-TTS voices for a model."""
return list(self.speakers.keys())
def healthcheck(self):
"""Return health/status info for F5-TTS engine."""
if self.model:
return {"status": "ok", "message": "F5-TTS engine is ready"}
else:
return {"status": "error", "message": "F5-TTS engine failed to initialize"}
async def selftest(self):
"""Run internal self-test for F5-TTS."""
if not self.model:
return {"status": "failed", "message": "F5-TTS Engine not initialized."}
try:
# Await the async synthesize method
audio_file = await self.synthesize("this is a test.")
selftest_passed = os.path.exists(audio_file) and os.path.getsize(audio_file) > 0
if selftest_passed:
os.remove(audio_file)
return {"status": "passed" if selftest_passed else "failed", "message": "F5-TTS self-test successful"}
except Exception as e:
return {"status": "failed", "message": f"F5-TTS self-test failed: {e}"}

163
app/engines/piper.py Normal file
View 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())

48
app/engines/styletts.py Normal file
View File

@ -0,0 +1,48 @@
"""
NovaAi – TTS-Engine-Hub
engines/styletts.py
Version: v0.0.1
Description:
StyleTTS engine adapter.
Implements TTSEngineBase interface for StyleTTS integration (dummy implementation).
Author: Abby (ChatGPT)
Date: 2025-07-23
Canvas: styletts.py
"""
import asyncio
from .engine_base import TTSEngineBase
class StyleTTSEngine(TTSEngineBase):
async def synthesize(self, text: str, speaker: str = None, model: str = None, fmt: str = "mp3"):
# Dummy implementation: returns an empty string as it doesn't produce a file.
print("Warning: StyleTTSEngine.synthesize is a dummy and does not produce audio.")
return ""
def list_models(self):
# Dummy implementation
return ["styletts_v2_de", "styletts_v2_en"]
def list_voices(self, model: str = None):
# Dummy implementation
return ["neutral", "emotional", "female"]
def healthcheck(self):
# Dummy implementation
return {"status": "ok", "engine": "styletts"}
async def selftest(self):
# Dummy implementation
return {"selftest": True, "engine": "styletts"}
if __name__ == "__main__":
async def main():
engine = StyleTTSEngine()
print("Selftest:", await engine.selftest())
print("Models:", engine.list_models())
print("Voices:", engine.list_voices())
print("Healthcheck:", engine.healthcheck())
asyncio.run(main())

18
app/main.py
View File

@ -21,14 +21,14 @@ import base64
import shutil
import uvicorn
from config import settings
from engines.piper import PiperEngine
from engines.styletts import StyleTTSEngine
from engines.chattts import ChatTTSEngine
from engines.f5_tts import F5TTSEngine
from utils.text import chunk_text
from utils.audio import concat_audio
from utils.cache import build_cache_key
from app.config import settings
from app.engines.piper import PiperEngine
from app.engines.styletts import StyleTTSEngine
from app.engines.chattts import ChatTTSEngine
from app.engines.f5_tts import F5TTSEngine
from app.utils.text import chunk_text
from app.utils.audio import concat_audio
from app.utils.cache import build_cache_key
# --- Master list of all possible engine classes. ---
ALL_ENGINES = {
@ -201,4 +201,6 @@ if __name__ == "__main__":
reload=True
)
app = create_app()

493
app/models/de_DE-thorsten-high/de_DE-thorsten-high.onnx.json Normal file
View File

@ -0,0 +1,493 @@
{
"audio": {
"sample_rate": 22050,
"quality": "high"
},
"espeak": {
"voice": "de"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "de_DE",
"family": "de",
"region": "DE",
"name_native": "Deutsch",
"name_english": "German",
"country_english": "Germany"
},
"dataset": "thorsten"
}

502
app/models/de_DE-thorsten_emotional-medium/de_DE-thorsten_emotional-medium.onnx.json Normal file
View File

@ -0,0 +1,502 @@
{
"piper_version": "1.1.0",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "de"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 8,
"speaker_id_map": {
"amused": 0,
"angry": 1,
"disgusted": 2,
"drunk": 3,
"neutral": 4,
"sleepy": 5,
"surprised": 6,
"whisper": 7
},
"language": {
"code": "de_DE",
"family": "de",
"region": "DE",
"name_native": "Deutsch",
"name_english": "German",
"country_english": "Germany"
},
"dataset": "thorsten_emotional"
}

502
app/models/en_GB-cori-high/en_GB-cori-high.onnx.json Normal file
View File

@ -0,0 +1,502 @@
{
"dataset": "cori",
"audio": {
"sample_rate": 22050,
"quality": "high"
},
"espeak": {
"voice": "en"
},
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}

603
app/models/en_GB-vctk-medium/en_GB-vctk-medium.onnx.json Normal file
View File

@ -0,0 +1,603 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-gb-x-rp"
},
"inference": {
"noise_scale": 0.333,
"length_scale": 1.4,
"noise_w": 0.333
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 109,
"speaker_id_map": {
"p239": 0,
"p236": 1,
"p264": 2,
"p250": 3,
"p259": 4,
"p247": 5,
"p261": 6,
"p263": 7,
"p283": 8,
"p286": 9,
"p274": 10,
"p276": 11,
"p270": 12,
"p281": 13,
"p277": 14,
"p231": 15,
"p271": 16,
"p238": 17,
"p257": 18,
"p273": 19,
"p284": 20,
"p329": 21,
"p361": 22,
"p287": 23,
"p360": 24,
"p374": 25,
"p376": 26,
"p310": 27,
"p304": 28,
"p334": 29,
"p340": 30,
"p323": 31,
"p347": 32,
"p330": 33,
"p308": 34,
"p314": 35,
"p317": 36,
"p339": 37,
"p311": 38,
"p294": 39,
"p305": 40,
"p266": 41,
"p335": 42,
"p318": 43,
"p351": 44,
"p333": 45,
"p313": 46,
"p316": 47,
"p244": 48,
"p307": 49,
"p363": 50,
"p336": 51,
"p297": 52,
"p312": 53,
"p267": 54,
"p275": 55,
"p295": 56,
"p258": 57,
"p288": 58,
"p301": 59,
"p232": 60,
"p292": 61,
"p272": 62,
"p280": 63,
"p278": 64,
"p341": 65,
"p268": 66,
"p298": 67,
"p299": 68,
"p279": 69,
"p285": 70,
"p326": 71,
"p300": 72,
"s5": 73,
"p230": 74,
"p345": 75,
"p254": 76,
"p269": 77,
"p293": 78,
"p252": 79,
"p262": 80,
"p243": 81,
"p227": 82,
"p343": 83,
"p255": 84,
"p229": 85,
"p240": 86,
"p248": 87,
"p253": 88,
"p233": 89,
"p228": 90,
"p282": 91,
"p251": 92,
"p246": 93,
"p234": 94,
"p226": 95,
"p260": 96,
"p245": 97,
"p241": 98,
"p303": 99,
"p265": 100,
"p306": 101,
"p237": 102,
"p249": 103,
"p256": 104,
"p302": 105,
"p364": 106,
"p225": 107,
"p362": 108
},
"piper_version": "1.0.0",
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"dataset": "vctk"
}

508
app/models/en_US-hfc_female-medium/en_US-hfc_female-medium.onnx.json Normal file
View File

@ -0,0 +1,508 @@
{
"dataset": "hfc_female",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-us"
},
"language": {
"code": "en_US",
"family": "en",
"region": "US",
"name_native": "English",
"name_english": "English",
"country_english": "United States"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̊": [
158
],
"̝": [
157
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}

502
app/models/en_US-kristin-medium/en_US-kristin-medium.onnx.json Normal file
View File

@ -0,0 +1,502 @@
{
"dataset": "kristin",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en"
},
"language": {
"code": "en_US",
"family": "en",
"region": "US",
"name_native": "English",
"name_english": "English",
"country_english": "United States"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}

493
app/models/piper/de_DE-thorsten-high/de_DE-thorsten-high.onnx.json Normal file
View File

@ -0,0 +1,493 @@
{
"audio": {
"sample_rate": 22050,
"quality": "high"
},
"espeak": {
"voice": "de"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "de_DE",
"family": "de",
"region": "DE",
"name_native": "Deutsch",
"name_english": "German",
"country_english": "Germany"
},
"dataset": "thorsten"
}

502
app/models/piper/de_DE-thorsten_emotional-medium/de_DE-thorsten_emotional-medium.onnx.json Normal file
View File

@ -0,0 +1,502 @@
{
"piper_version": "1.1.0",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "de"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 8,
"speaker_id_map": {
"amused": 0,
"angry": 1,
"disgusted": 2,
"drunk": 3,
"neutral": 4,
"sleepy": 5,
"surprised": 6,
"whisper": 7
},
"language": {
"code": "de_DE",
"family": "de",
"region": "DE",
"name_native": "Deutsch",
"name_english": "German",
"country_english": "Germany"
},
"dataset": "thorsten_emotional"
}

502
app/models/piper/en_GB-cori-high/en_GB-cori-high.onnx.json Normal file
View File

@ -0,0 +1,502 @@
{
"dataset": "cori",
"audio": {
"sample_rate": 22050,
"quality": "high"
},
"espeak": {
"voice": "en"
},
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}

603
app/models/piper/en_GB-vctk-medium/en_GB-vctk-medium.onnx.json Normal file
View File

@ -0,0 +1,603 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-gb-x-rp"
},
"inference": {
"noise_scale": 0.333,
"length_scale": 1.4,
"noise_w": 0.333
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 109,
"speaker_id_map": {
"p239": 0,
"p236": 1,
"p264": 2,
"p250": 3,
"p259": 4,
"p247": 5,
"p261": 6,
"p263": 7,
"p283": 8,
"p286": 9,
"p274": 10,
"p276": 11,
"p270": 12,
"p281": 13,
"p277": 14,
"p231": 15,
"p271": 16,
"p238": 17,
"p257": 18,
"p273": 19,
"p284": 20,
"p329": 21,
"p361": 22,
"p287": 23,
"p360": 24,
"p374": 25,
"p376": 26,
"p310": 27,
"p304": 28,
"p334": 29,
"p340": 30,
"p323": 31,
"p347": 32,
"p330": 33,
"p308": 34,
"p314": 35,
"p317": 36,
"p339": 37,
"p311": 38,
"p294": 39,
"p305": 40,
"p266": 41,
"p335": 42,
"p318": 43,
"p351": 44,
"p333": 45,
"p313": 46,
"p316": 47,
"p244": 48,
"p307": 49,
"p363": 50,
"p336": 51,
"p297": 52,
"p312": 53,
"p267": 54,
"p275": 55,
"p295": 56,
"p258": 57,
"p288": 58,
"p301": 59,
"p232": 60,
"p292": 61,
"p272": 62,
"p280": 63,
"p278": 64,
"p341": 65,
"p268": 66,
"p298": 67,
"p299": 68,
"p279": 69,
"p285": 70,
"p326": 71,
"p300": 72,
"s5": 73,
"p230": 74,
"p345": 75,
"p254": 76,
"p269": 77,
"p293": 78,
"p252": 79,
"p262": 80,
"p243": 81,
"p227": 82,
"p343": 83,
"p255": 84,
"p229": 85,
"p240": 86,
"p248": 87,
"p253": 88,
"p233": 89,
"p228": 90,
"p282": 91,
"p251": 92,
"p246": 93,
"p234": 94,
"p226": 95,
"p260": 96,
"p245": 97,
"p241": 98,
"p303": 99,
"p265": 100,
"p306": 101,
"p237": 102,
"p249": 103,
"p256": 104,
"p302": 105,
"p364": 106,
"p225": 107,
"p362": 108
},
"piper_version": "1.0.0",
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"dataset": "vctk"
}

508
app/models/piper/en_US-hfc_female-medium/en_US-hfc_female-medium.onnx.json Normal file
View File

@ -0,0 +1,508 @@
{
"dataset": "hfc_female",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-us"
},
"language": {
"code": "en_US",
"family": "en",
"region": "US",
"name_native": "English",
"name_english": "English",
"country_english": "United States"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̊": [
158
],
"̝": [
157
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}

502
app/models/piper/en_US-kristin-medium/en_US-kristin-medium.onnx.json Normal file
View File

@ -0,0 +1,502 @@
{
"dataset": "kristin",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en"
},
"language": {
"code": "en_US",
"family": "en",
"region": "US",
"name_native": "English",
"name_english": "English",
"country_english": "United States"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}

76
app/utils/audio.py Normal file
View File

@ -0,0 +1,76 @@
"""
NovaAi – TTS-Engine-Hub
utils/audio.py
Version: v0.0.1
Description:
Audio processing utilities: concat, merging chunks, etc.
Author: Abby (ChatGPT)
Date: 2025-07-23
Canvas: utils/audio.py
"""
import tempfile
import os
import ffmpeg
import shutil
def check_ffmpeg():
"""Check if ffmpeg is installed and available in the system's PATH."""
return shutil.which("ffmpeg") is not None
def concat_audio(files, fmt):
"""
Concatenate a list of audio files into a single file of the given format.
Supports: wav, ogg, mp3
"""
if len(files) == 1:
# If there's only one file, just return it, no cleanup needed here.
return files[0]
# Securely create a temporary file for the output
with tempfile.NamedTemporaryFile(suffix=f'.{fmt}', prefix="chunked_", delete=False) as temp_output_file:
output_file_path = temp_output_file.name
try:
if fmt == "wav":
import wave
data = []
params = None
for f in files:
with wave.open(f, 'rb') as wf:
if params is None:
params = wf.getparams()
data.append(wf.readframes(wf.getnframes()))
with wave.open(output_file_path, 'wb') as wf:
wf.setparams(params)
for d in data:
wf.writeframes(d)
else:
if not check_ffmpeg():
raise RuntimeError("ffmpeg not found. Please install ffmpeg and ensure it is in your PATH.")
with tempfile.NamedTemporaryFile("w", delete=False) as tf:
list_file_path = tf.name
for f in files:
tf.write(f"file '{os.path.abspath(f)}'\\n")
tf.flush()
try:
(
ffmpeg
.input(list_file_path, format='concat', safe=0)
.output(output_file_path, acodec='copy')
.run(overwrite_output=True, quiet=True)
)
finally:
os.unlink(list_file_path)
finally:
# Clean up the input chunk files
for f in files:
if os.path.exists(f):
os.remove(f)
return output_file_path

22
app/utils/cache.py Normal file
View File

@ -0,0 +1,22 @@
"""
NovaAi – TTS-Engine-Hub
utils/cache.py
Version: v0.0.1
Description:
Caching utilities for TTS requests (cache key generation, etc).
Author: Abby (ChatGPT)
Date: 2025-07-23
Canvas: utils/cache.py
"""
import hashlib
# Für die API: Wichtig! req muss mindestens die Felder .text, .engine, .model, .speaker, .format, .chunking haben.
def build_cache_key(req) -> str:
"""
Build a cache key from all relevant TTS request parameters.
"""
data = f"{req.text}|{req.engine}|{req.model}|{req.speaker}|{req.format}|{getattr(req, 'chunking', False)}"
return hashlib.sha256(data.encode()).hexdigest()

30
app/utils/text.py Normal file
View File

@ -0,0 +1,30 @@
"""
NovaAi – TTS-Engine-Hub
utils/text.py
Version: v0.0.1
Description:
Text processing utilities: chunking, splitting, etc.
Author: Abby (ChatGPT)
Date: 2025-07-23
Canvas: utils/text.py
"""
def chunk_text(text, maxlen=250):
"""
Split text into chunks of roughly maxlen (split at sentence boundaries if possible).
"""
import re
sentences = re.split(r'([.!?]\s)', text)
chunks = []
buf = ""
for s in sentences:
if len(buf) + len(s) > maxlen:
if buf:
chunks.append(buf.strip())
buf = ""
buf += s
if buf.strip():
chunks.append(buf.strip())
return [c for c in chunks if c.strip()]