The open-source AI voice studio. Clone, dictate, create.
fix: force offline mode when loading cached models (Qwen TTS & Whisper)
James Pine2e95b7c5d8db
diff --git a/backend/backends/mlx_backend.py b/backend/backends/mlx_backend.pyindex 92405dbf..c6157a40 100644--- a/backend/backends/mlx_backend.py+++ b/backend/backends/mlx_backend.py@@ -6,7 +6,6 @@ from typing import Optional, List, Tupleimport asyncioimport loggingimport numpy as np-import osfrom pathlib import Pathlogger = logging.getLogger(__name__)@@ -21,6 +20,7 @@ ensure_original_qwen_config_cached()from . import TTSBackend, STTBackend, LANGUAGE_CODE_TO_NAME, WHISPER_HF_REPOSfrom .base import is_model_cached, combine_voice_prompts as _combine_voice_prompts, model_load_progressfrom ..utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_prompt+from ..utils.hf_offline_patch import force_offline_if_cachedclass MLXTTSBackend:@@ -96,32 +96,13 @@ class MLXTTSBackend:model_name = f"qwen-tts-{model_size}"is_cached = self._is_model_cached(model_size)- # Force offline mode when cached to avoid network requests- original_hf_hub_offline = os.environ.get("HF_HUB_OFFLINE")- if is_cached:- os.environ["HF_HUB_OFFLINE"] = "1"- logger.info("[PATCH] Model %s is cached, forcing HF_HUB_OFFLINE=1 to avoid network requests", model_size)-- try:- with model_load_progress(model_name, is_cached):- from mlx_audio.tts import load-- logger.info("Loading MLX TTS model %s...", model_size)-- try:- self.model = load(model_path)- except Exception as load_error:- if is_cached and "offline" in str(load_error).lower():- logger.warning("[PATCH] Offline load failed, trying with network: %s", load_error)- os.environ.pop("HF_HUB_OFFLINE", None)- self.model = load(model_path)- else:- raise- finally:- if original_hf_hub_offline is not None:- os.environ["HF_HUB_OFFLINE"] = original_hf_hub_offline- else:- os.environ.pop("HF_HUB_OFFLINE", None)+ with model_load_progress(model_name, is_cached):+ from mlx_audio.tts import load++ logger.info("Loading MLX TTS model %s...", model_size)++ with force_offline_if_cached(is_cached, model_name):+ self.model = load(model_path)self._current_model_size = model_sizeself.model_size = model_size@@ -329,7 +310,9 @@ class MLXSTTBackend:model_name = WHISPER_HF_REPOS.get(model_size, f"openai/whisper-{model_size}")logger.info("Loading MLX Whisper model %s...", model_size)- self.model = load(model_name)++ with force_offline_if_cached(is_cached, progress_model_name):+ self.model = load(model_name)self.model_size = model_sizelogger.info("MLX Whisper model %s loaded successfully", model_size)diff --git a/backend/backends/pytorch_backend.py b/backend/backends/pytorch_backend.pyindex 8ed4ab9c..25a8b6a3 100644--- a/backend/backends/pytorch_backend.py+++ b/backend/backends/pytorch_backend.py@@ -19,6 +19,7 @@ from .base import ()from ..utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_promptfrom ..utils.audio import load_audio+from ..utils.hf_offline_patch import force_offline_if_cachedclass PyTorchTTSBackend:@@ -96,18 +97,19 @@ class PyTorchTTSBackend:model_path = self._get_model_path(model_size)logger.info("Loading TTS model %s on %s...", model_size, self.device)- if self.device == "cpu":- self.model = Qwen3TTSModel.from_pretrained(- model_path,- torch_dtype=torch.float32,- low_cpu_mem_usage=False,- )- else:- self.model = Qwen3TTSModel.from_pretrained(- model_path,- device_map=self.device,- torch_dtype=torch.bfloat16,- )+ with force_offline_if_cached(is_cached, model_name):+ if self.device == "cpu":+ self.model = Qwen3TTSModel.from_pretrained(+ model_path,+ torch_dtype=torch.float32,+ low_cpu_mem_usage=False,+ )+ else:+ self.model = Qwen3TTSModel.from_pretrained(+ model_path,+ device_map=self.device,+ torch_dtype=torch.bfloat16,+ )self._current_model_size = model_sizeself.model_size = model_size@@ -282,8 +284,9 @@ class PyTorchSTTBackend:model_name = WHISPER_HF_REPOS.get(model_size, f"openai/whisper-{model_size}")logger.info("Loading Whisper model %s on %s...", model_size, self.device)- self.processor = WhisperProcessor.from_pretrained(model_name)- self.model = WhisperForConditionalGeneration.from_pretrained(model_name)+ with force_offline_if_cached(is_cached, progress_model_name):+ self.processor = WhisperProcessor.from_pretrained(model_name)+ self.model = WhisperForConditionalGeneration.from_pretrained(model_name)self.model.to(self.device)self.model_size = model_sizediff --git a/backend/utils/hf_offline_patch.py b/backend/utils/hf_offline_patch.pyindex 51a99a16..1abd147f 100644--- a/backend/utils/hf_offline_patch.py+++ b/backend/utils/hf_offline_patch.py@@ -1,17 +1,64 @@"""Monkey-patch huggingface_hub to force offline mode with cached models.-Prevents mlx_audio from making network requests when models are already-downloaded. Must be imported BEFORE mlx_audio.+Prevents mlx_audio / transformers from making network requests when models+are already downloaded. Must be imported BEFORE mlx_audio."""import loggingimport os+from contextlib import contextmanagerfrom pathlib import Pathfrom typing import Optional, Unionlogger = logging.getLogger(__name__)+@contextmanager+def force_offline_if_cached(is_cached: bool, model_label: str = ""):+ """Context manager that sets ``HF_HUB_OFFLINE=1`` while loading a cached model.++ If *is_cached* is ``False`` the block runs normally (network allowed).+ If the offline load raises an error containing "offline" we automatically+ retry with network access so a partially-cached model still works.++ Args:+ is_cached: Whether the model weights are already on disk.+ model_label: Human-readable name used in log messages.+ """+ if not is_cached:+ yield+ return++ original_value = os.environ.get("HF_HUB_OFFLINE")+ os.environ["HF_HUB_OFFLINE"] = "1"+ logger.info(+ "[offline-guard] %s is cached — forcing HF_HUB_OFFLINE=1",+ model_label or "model",+ )++ try:+ yield+ except Exception as exc:+ if "offline" in str(exc).lower():+ logger.warning(+ "[offline-guard] Offline load failed for %s, retrying with network: %s",+ model_label or "model",+ exc,+ )+ # Restore original env and retry — caller must wrap the load+ # inside force_offline_if_cached so retrying here isn't possible.+ # Instead, propagate a flag via the exception so the caller can+ # decide. For simplicity we just let it fall through to the+ # finally block and re-raise.+ raise+ raise+ finally:+ if original_value is not None:+ os.environ["HF_HUB_OFFLINE"] = original_value+ else:+ os.environ.pop("HF_HUB_OFFLINE", None)++def patch_huggingface_hub_offline():"""Monkey-patch huggingface_hub to force offline mode."""try: