Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-10-03 17:15:19 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

Browse Source
This commit is contained in:
devangkantharia
2026-10-04 00:01:18 +00:00
committed by capy-ai-staging[bot]
parent 63f09455ef
commit 38389db82b
8 changed files with 88 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/backends/chatterbox_backend.py
+15 -14
View File
@@ -203,21 +203,22 @@ class ChatterboxTTSBackend:
logger.info(f"[Chatterbox] Generating: lang={language}")
wav = self.model.generate(
text,
language_id=language,
audio_prompt_path=ref_audio,
exaggeration=lang_defaults["exaggeration"],
cfg_weight=lang_defaults["cfg_weight"],
temperature=lang_defaults["temperature"],
repetition_penalty=lang_defaults["repetition_penalty"],
)
with torch.inference_mode():
wav = self.model.generate(
text,
language_id=language,
audio_prompt_path=ref_audio,
exaggeration=lang_defaults["exaggeration"],
cfg_weight=lang_defaults["cfg_weight"],
temperature=lang_defaults["temperature"],
repetition_penalty=lang_defaults["repetition_penalty"],
)
# Convert tensor -> numpy
if isinstance(wav, torch.Tensor):
audio = wav.squeeze().cpu().numpy().astype(np.float32)
else:
audio = np.asarray(wav, dtype=np.float32)
# Convert tensor -> numpy
if isinstance(wav, torch.Tensor):
audio = wav.squeeze().cpu().numpy().astype(np.float32)
else:
audio = np.asarray(wav, dtype=np.float32)
sample_rate = getattr(self.model, "sr", None) or getattr(self.model, "sample_rate", 24000)