Active code page: 65001
D:\f5 tts\runtime\Lib\site-packages\google\api_core\_python_version_support.py:266: FutureWarning: You are using a Python version (3.10.11) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
warnings.warn(message, FutureWarning)
Load vocos from local path D:/f5 tts/ckpts
vocab : D:\f5 tts\src\f5_tts\infer\examples\vocab.txt
token : custom
model : D:\f5 tts\ckpts\models--SWivid--F5-TTS\snapshots\84e5a410d9cead4de2f847e7c9369a6440bdfaca\F5TTS_v1_Base\model_1250000.safetensors
Traceback (most recent call last):
File "D:\f5 tts\src\f5_tts\infer\infer_gradio.py", line 96, in
F5TTS_ema_model = load_f5tts()
File "D:\f5 tts\src\f5_tts\infer\infer_gradio.py", line 74, in load_f5tts
return load_model(DiT, F5TTS_model_cfg, ckpt_path)
File "D:\f5 tts\src\f5_tts\infer\utils_infer.py", line 234, in load_model
model = load_checkpoint(model, ckpt_path, device, dtype=dtype, use_ema=use_ema)
File "D:\f5 tts\src\f5_tts\infer\utils_infer.py", line 165, in load_checkpoint
checkpoint = load_file(ckpt_path, device=device)
File "D:\f5 tts\runtime\Lib\site-packages\safetensors\torch.py", line 336, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: header too small