I get this error message when I try to transcribe a 1 minutes voice. here are the codes:
model_id = ""openai/whisper-small""
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=128,
chunk_length_s=30,
batch_size=16,
return_timestamps=True,
torch_dtype=torch_dtype,
device=device,
)
pipe(audio_file, return_timestamps=True, generate_kwargs={"language": "German"})
Is this important? What can I do about this message? What does this mean and why happens?
Thank you for your answers and discussions.