Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-10-03 00:55:14 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(qwen): unify HF cache dir to avoid split cache on Windows

Browse Source 
Applies the cache_dir portion of #218. On Windows local setups, model
assets can split between .hf-cache/hub and .hf-cache/transformers when
Qwen3TTSModel.from_pretrained doesn't explicitly pin the cache root —
speech_tokenizer and preprocessor_config.json then fail to resolve
during load, causing 500s at generation time.

Routes both HF Hub and Transformers through hf_constants.HF_HUB_CACHE.

Skipped the torch_dtype= → dtype= rename from #218: transformers 4.36
(our minimum) doesn't accept the dtype alias, only 4.46+. Once we bump
the minimum we can make that change.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
This commit is contained in:
James Pine
2026-04-16 02:08:59 -07:00
co-authored by Claude Opus 4.6
parent a5d5c780c2
commit 0317626677
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/backends/pytorch_backend.py
+9
View File
@@ -99,16 +99,25 @@ class PyTorchTTSBackend:
model_path = self._get_model_path(model_size) model_path = self._get_model_path(model_size)
logger.info("Loading TTS model %s on %s...", model_size, self.device) logger.info("Loading TTS model %s on %s...", model_size, self.device)
# Route both HF Hub and Transformers through a single cache root.
# On Windows local setups, model assets can otherwise split between
# .hf-cache/hub and .hf-cache/transformers, causing speech_tokenizer
# and preprocessor_config.json to fail to resolve during load.
from huggingface_hub import constants as hf_constants
tts_cache_dir = hf_constants.HF_HUB_CACHE
with force_offline_if_cached(is_cached, model_name): with force_offline_if_cached(is_cached, model_name):
if self.device == "cpu": if self.device == "cpu":
self.model = Qwen3TTSModel.from_pretrained( self.model = Qwen3TTSModel.from_pretrained(
model_path, model_path,
cache_dir=tts_cache_dir,
torch_dtype=torch.float32, torch_dtype=torch.float32,
low_cpu_mem_usage=False, low_cpu_mem_usage=False,
) )
else: else:
self.model = Qwen3TTSModel.from_pretrained( self.model = Qwen3TTSModel.from_pretrained(
model_path, model_path,
cache_dir=tts_cache_dir,
device_map=self.device, device_map=self.device,
torch_dtype=torch.bfloat16, torch_dtype=torch.bfloat16,
) )