liteASR/run_eval.py [21:60]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    elif args.max_new_tokens:
        raise ValueError("`max_new_tokens` should only be set for auto-regressive models, but got a CTC model.")

    if args.torch_compile:
        model.forward = torch.compile(model.forward, mode=args.compile_mode, fullgraph=True)
        if model.can_generate():
            # enable static k/v cache for autoregressive models
            model.generation_config.cache_implementation = "static"

    def benchmark(batch, min_new_tokens=None):
        # Load audio inputs
        audios = [audio["array"] for audio in batch["audio"]]
        minibatch_size = len(audios)

        # START TIMING
        start_time = time.time()

        # 1. Pre-Processing
        # 1.1 Pad audios to max batch size if using torch compile to prevent re-compilations
        padding_size = None
        if minibatch_size != args.batch_size and args.torch_compile:
            padding_size = args.batch_size - minibatch_size
            padding_audios = [audios[-1] for _ in range(padding_size)]
            audios.extend(padding_audios)

        if not model.can_generate(): #or len(audios[0]) > processor.feature_extractor.n_samples:
            # 1.2 Either CTC pre-processing (normalize to mean 0, std 1), or long-form Whisper processing
            inputs = processor(
                audios,
                sampling_rate=16_000,
                truncation=False,
                padding="longest",
                return_tensors="pt",
                return_attention_mask=True,
            )
        else:
            # 1.3 Standard Whisper processing: pad audios to 30-seconds and converted to log-mel
            inputs = processor(audios, sampling_rate=16_000, return_tensors="pt", device=args.device)

        inputs = inputs.to(args.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



transformers/run_eval.py [27:66]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    elif args.max_new_tokens:
        raise ValueError("`max_new_tokens` should only be set for auto-regressive models, but got a CTC model.")

    if args.torch_compile:
        model.forward = torch.compile(model.forward, mode=args.compile_mode, fullgraph=True)
        if model.can_generate():
            # enable static k/v cache for autoregressive models
            model.generation_config.cache_implementation = "static"

    def benchmark(batch, min_new_tokens=None):
        # Load audio inputs
        audios = [audio["array"] for audio in batch["audio"]]
        minibatch_size = len(audios)

        # START TIMING
        start_time = time.time()

        # 1. Pre-Processing
        # 1.1 Pad audios to max batch size if using torch compile to prevent re-compilations
        padding_size = None
        if minibatch_size != args.batch_size and args.torch_compile:
            padding_size = args.batch_size - minibatch_size
            padding_audios = [audios[-1] for _ in range(padding_size)]
            audios.extend(padding_audios)

        if not model.can_generate(): #or len(audios[0]) > processor.feature_extractor.n_samples:
            # 1.2 Either CTC pre-processing (normalize to mean 0, std 1), or long-form Whisper processing
            inputs = processor(
                audios,
                sampling_rate=16_000,
                truncation=False,
                padding="longest",
                return_tensors="pt",
                return_attention_mask=True,
            )
        else:
            # 1.3 Standard Whisper processing: pad audios to 30-seconds and converted to log-mel
            inputs = processor(audios, sampling_rate=16_000, return_tensors="pt", device=args.device)

        inputs = inputs.to(args.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -