bhetherman/voice-assistant-stack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Pin tts-server Sopro model to a known-good HF revision

Browse Source 
Loading from the unpinned main branch let an upstream repo restructure
(dropped vocoder_streaming.safetensors) crash-loop the tts container on
every boot for days; pin to the last snapshot with the full file set.
This commit is contained in:
bhetherman
2026-09-27 02:02:43 -04:00
parent 2b05169b66
commit e845016b32
1 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tts-server/app.py
+10 -2
View File
@@ -50,8 +50,16 @@ log.info("Loading Kokoro (lang_code=%s) on %s", LANG_CODE, DEVICE)
kokoro_pipeline = KPipeline(lang_code=LANG_CODE, device=DEVICE)
log.info("Kokoro ready")
log.info("Loading Sopro on %s", DEVICE)
sopro_model = SoproTTS.from_pretrained("samuel-vitorino/sopro-v2-turbo", device=DEVICE)
# Pinned instead of tracking the mutable `main` branch: upstream restructured
# the repo on 2026-09-15 (dropped/renamed vocoder_streaming.safetensors and
# speaker_encoder.safetensors), which crash-looped this container on every
# boot since the unpinned load kept re-fetching the broken layout.
SOPRO_REVISION = os.environ.get("TTS_SOPRO_REVISION", "ceeeb86b5fd805e662a5a750d6053ac4f990a45a")
log.info("Loading Sopro on %s (revision=%s)", DEVICE, SOPRO_REVISION)
sopro_model = SoproTTS.from_pretrained(
"samuel-vitorino/sopro-v2-turbo", device=DEVICE, revision=SOPRO_REVISION
)
log.info("Sopro ready")
# References are just resampled/cropped tensors of the voice clip -- cheap to