Method preprocess

buzz/transformers_whisper.py:60–180

(self, inputs, chunk_length_s=0, stride_length_s=None)

    # Copy of transformers `AutomaticSpeechRecognitionPipeline.preprocess` method with call to custom `chunk_iter`
    def preprocess(self, inputs, chunk_length_s=0, stride_length_s=None):
        if isinstance(inputs, str):
            if inputs.startswith("http://") or inputs.startswith("https://"):
                # We need to actually check for a real protocol, otherwise it's impossible to use a local file
                # like http_huggingface_co.png
                inputs = requests.get(inputs).content
            else:
                with open(inputs, "rb") as f:
                    inputs = f.read()

        if isinstance(inputs, bytes):
            inputs = ffmpeg_read(inputs, self.feature_extractor.sampling_rate)

        stride = None
        extra = {}
        if isinstance(inputs, dict):
            stride = inputs.pop("stride", None)
            # Accepting `"array"` which is the key defined in `datasets` for
            # better integration
            if not ("sampling_rate" in inputs and ("raw" in inputs or "array" in inputs)):
                raise ValueError(
                    "When passing a dictionary to AutomaticSpeechRecognitionPipeline, the dict needs to contain a "
                    '"raw" key containing the numpy array representing the audio and a "sampling_rate" key, '
                    "containing the sampling_rate associated with that array"
                )

            _inputs = inputs.pop("raw", None)
            if _inputs is None:
                # Remove path which will not be used from `datasets`.
                inputs.pop("path", None)
                _inputs = inputs.pop("array", None)
            in_sampling_rate = inputs.pop("sampling_rate")
            extra = inputs
            inputs = _inputs
            if in_sampling_rate != self.feature_extractor.sampling_rate:
                if is_torchaudio_available():
                    from torchaudio import functional as F
                else:
                    raise ImportError(
                        "torchaudio is required to resample audio samples in AutomaticSpeechRecognitionPipeline. "
                        "The torchaudio package can be installed through: `pip install torchaudio`."
                    )

                inputs = F.resample(
                    torch.from_numpy(inputs), in_sampling_rate, self.feature_extractor.sampling_rate
                ).numpy()
                ratio = self.feature_extractor.sampling_rate / in_sampling_rate
            else:
                ratio = 1
            if stride is not None:
                if stride[0] + stride[1] > inputs.shape[0]:
                    raise ValueError("Stride is too large for input")

                # Stride needs to get the chunk length here, it's going to get
                # swallowed by the `feature_extractor` later, and then batching
                # can add extra data in the inputs, so we need to keep track
                # of the original length in the stride so we can cut properly.
                stride = (inputs.shape[0], int(round(stride[0] * ratio)), int(round(stride[1] * ratio)))