engineering/uncloseai-speech
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add voices-qwen Makefile target to download cloned voice samples

Browse source 
Runs scripts/download_diverse_voices.py which pulls speaker samples
from LibriSpeech and assigns permanent human names via voice registry.
Works with venv or system python. Also adds Voices section to help.
This commit is contained in:
russell@unturf.com 2026-01-27 17:31:15 -05:00
parent f58da54fa3
commit 7e77c3452d
1 changed files with 15 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

22
Makefile
View file

@ -27,15 +27,18 @@ help:
@echo " make hydrate - Test all configured voices"
@echo " make load-test - Concurrent load test"
@echo ""
@echo "Other Engines (disabled by default):"
@echo " make test-xtts - Test XTTS HD endpoint"
@echo " make test-kokoro - Test Kokoro fast TTS"
@echo " make test-silero - Test Silero TTS endpoint"
@echo "Voices:"
@echo " make voices-qwen - Download Qwen3-TTS cloned voice samples"
@echo " make voices-piper - Download Piper voices"
@echo " make voices-xtts - Download XTTS voices"
@echo " make voices-kokoro - Download Kokoro models"
@echo " make voices-silero - Download Silero models"
@echo ""
@echo "Other Engines (disabled by default):"
@echo " make test-xtts - Test XTTS HD endpoint"
@echo " make test-kokoro - Test Kokoro fast TTS"
@echo " make test-silero - Test Silero TTS endpoint"
@echo ""
@echo "Git:"
@echo " make push-all - Push to all git remotes"
@ -159,9 +162,14 @@ voices: voices-qwen
@echo "Qwen3-TTS ready (model downloads automatically on first use)"
voices-qwen:
@echo "Qwen3-TTS models download automatically on first use"
@echo " Model: Qwen/Qwen3-TTS-12Hz-1.7B-Base (~3.4GB)"
@echo " To pre-download, run: make test-qwen"
@echo "Downloading Qwen3-TTS voice samples from LibriSpeech..."
@if [ -d ".venv" ]; then \
.venv/bin/python scripts/download_diverse_voices.py; \
else \
python3 scripts/download_diverse_voices.py; \
fi
@echo "Qwen3-TTS voice samples ready in cloned-voices/"
@echo " Model (~3.4GB) downloads automatically on first use"
voices-all: voices-qwen voices-piper voices-xtts voices-silero
@echo "All voices downloaded!"