Russell Ballestrini
01e51b08b5
✅ Integrated Silero TTS as tts-1-silero model - Fixed omegaconf dependency - Fixed Silero API integration (torch.hub.load returns 2 values) - Fixed model.to(device) returning None bug - Mapped all 140 Silero voices across 5 languages: * English (en): 118 speakers (en_0 to en_117) + random * Russian (ru): 5 speakers (aidar, baya, kseniya, xenia, eugene) + random * German (de): 5 speakers (bernd_ungerer, eva_k, friedrich, hokuspokus, karlsson) + random * Spanish (es): 3 speakers (es_0, es_1, es_2) + random * French (fr): 6 speakers (fr_0 to fr_5) + random 📝 Configuration changes: - requirements.txt: Added omegaconf for Silero - voice_to_speaker.default.yaml: All 140 Silero voices mapped - speech.py: Silero wrapper class with proper API handling 🎯 Working TTS engines: 3 - Piper TTS (tts-1) - Fast, lightweight - XTTS v2 (tts-1-hd) - High quality, voice cloning - Silero TTS (tts-1-silero) - CPU-friendly, 5 languages, actively maintained 🦝 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
36 lines
1.6 KiB
Text
36 lines
1.6 KiB
Text
fastapi
|
|
uvicorn
|
|
loguru
|
|
# OHF-Voice fork doesn't have installable Python package yet
|
|
# Stick with PyPI piper-tts but use absolute paths in config
|
|
piper-tts>=1.2.0
|
|
# 🦝 RACCOON TODO: Create our own PyPI package from OHF-Voice fork
|
|
# git+https://github.com/OHF-Voice/piper1-gpl.git@v1.3.0#subdirectory=src/python_run
|
|
coqui-tts[languages]
|
|
# Silero TTS - actively maintained, small efficient models
|
|
# Note: Silero models are loaded via torch.hub, no package install needed
|
|
# Models: ~50-100MB each, CPU-friendly, real-time capable
|
|
omegaconf # Required by Silero TTS
|
|
# Chatterbox - emotion control, 23 languages (Resemble AI)
|
|
# Install from git since no PyPI package exists yet
|
|
# 🦝 RACCOON NOTE: Disabled due to dependency conflict with Coqui TTS
|
|
# gradio 5.44.1 requires typer<1.0 and >=0.12, but spacy 3.6.x requires typer<0.10.0
|
|
# TODO: Test Chatterbox in isolated environment or wait for dependency updates
|
|
# git+https://github.com/resemble-ai/chatterbox.git
|
|
langdetect
|
|
pyyaml
|
|
# Kokoro TTS - fast decoder-only architecture
|
|
# Install from Hugging Face transformers
|
|
transformers>=4.35.0
|
|
# Hugging Face Hub for model downloads
|
|
huggingface-hub[cli]
|
|
# Creating an environment where deepspeed works is complex, for now it will be disabled by default.
|
|
#deepspeed
|
|
|
|
torch; sys_platform != "darwin"
|
|
torchaudio; sys_platform != "darwin"
|
|
# for MPS accelerated torch on Mac - doesn't work yet, incomplete support in torch and torchaudio
|
|
torch; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
|
|
torchaudio; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
|
|
|
|
# ROCM (Linux only) - use requirements.amd.txt
|