Russell Ballestrini
a0e94be7af
OHF-Voice/piper1-gpl doesn't have installable Python package structure yet. The real fix is using ABSOLUTE paths in voice_to_speaker.yaml, not newer Piper version. Solution: Use /app/voices/en/en_US/libritts_r/medium/en_US-libritts_r-medium.onnx Co-Authored-By: Claude <noreply@anthropic.com>
19 lines
697 B
Text
19 lines
697 B
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
|
|
coqui-tts[languages]
|
|
langdetect
|
|
pyyaml
|
|
# 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
|