| ```diff | |
| import torch | |
| from transformers import WhisperForConditionalGeneration, WhisperProcessor | |
| device = "cuda:0" if torch.cuda.is_available() else "cpu" | |
| torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32 | |
| model_id = "openai/whisper-large-v3" | |
| model = AutoModelForSpeechSeq2Seq.from_pretrained( | |
| model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True | |
| ).to(device) | |
| + model.generation_config.cache_implementation = "static" | |
| + model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True) | |
| processor = AutoProcessor.from_pretrained(model_id) | |
| pipe = pipeline( | |
| "automatic-speech-recognition", | |
| model=model, | |
| tokenizer=processor.tokenizer, | |
| feature_extractor=processor.feature_extractor, | |
| torch_dtype=torch_dtype, | |
| device=device, | |
| ) | |
| dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation") | |
| sample = dataset[0]["audio"] | |
| result = pipe(sample) | |
| print(result["text"]) | |
| ``` | |
| <hfoptions id="gpu-select"> | |
| <hfoption id="CUDA GPU"> | |
| cuda code example | |
| </hfoption> | |
| <hfoption id="MPS"> | |
| mps code example | |
| </hfoption> | |
| </hfoptions> |