I get a FutureWarning: You are using `torch.load` with `weights_only=False` #2462

EncoreUnNerd · 2024-12-01T15:39:30Z

EncoreUnNerd
Dec 1, 2024

I try to use Whisper with this code :

import whisper
import os

def transcribe(audio_path: str):
	try:
		os.environ["TOKENIZERS_PARALLELISM"] = "false"
		model = whisper.load_model("small", device="cpu")

		options = { "fp16": False, "language": "fr"}
		result = model.transcribe(audio_path, **options)
		
		output_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "result", "test1.txt")
		
		with open(output_path, "w", encoding="utf-8") as w:
			w.write(result["text"])
			return output_path
		
	except Exception as e:
		print(f"Error during transcription: {str(e)}")
		return None

and i get this error :

FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  checkpoint = torch.load(fp, map_location=device)

my cde still work but i get this warning in my term and i dont like it, i searched online and didn't find a solution, im a newbie using whisper and anything related to pytorch so if it's to complicated i may take some time to understand

If know the answer, thank's a lot