def __init__()

in whisper/decoding.py [0:0]

• 45 lines of code
• 12 McCabe index (conditional complexity)

    def __init__(self, model: "Whisper", options: DecodingOptions):
        self.model = model

        language = options.language or "en"
        tokenizer = get_tokenizer(
            model.is_multilingual,
            num_languages=model.num_languages,
            language=language,
            task=options.task,
        )
        self.tokenizer: Tokenizer = tokenizer
        self.options: DecodingOptions = self._verify_options(options)

        self.n_group: int = options.beam_size or options.best_of or 1
        self.n_ctx: int = model.dims.n_text_ctx
        self.sample_len: int = options.sample_len or model.dims.n_text_ctx // 2

        self.sot_sequence: Tuple[int] = tokenizer.sot_sequence
        if self.options.without_timestamps:
            self.sot_sequence = tokenizer.sot_sequence_including_notimestamps

        self.initial_tokens: Tuple[int] = self._get_initial_tokens()
        self.sample_begin: int = len(self.initial_tokens)
        self.sot_index: int = self.initial_tokens.index(tokenizer.sot)

        # inference: implements the forward pass through the decoder, including kv caching
        self.inference = PyTorchInference(model, len(self.initial_tokens))

        # sequence ranker: implements how to rank a group of sampled sequences
        self.sequence_ranker = MaximumLikelihoodRanker(options.length_penalty)

        # decoder: implements how to select the next tokens, given the autoregressive distribution
        if options.beam_size is not None:
            self.decoder = BeamSearchDecoder(
                options.beam_size, tokenizer.eot, self.inference, options.patience
            )
        else:
            self.decoder = GreedyDecoder(options.temperature, tokenizer.eot)

        # logit filters: applies various rules to suppress or penalize certain tokens
        self.logit_filters = []
        if self.options.suppress_blank:
            self.logit_filters.append(SuppressBlank(self.tokenizer, self.sample_begin))
        if self.options.suppress_tokens:
            self.logit_filters.append(SuppressTokens(self._get_suppress_tokens()))
        if not options.without_timestamps:
            precision = CHUNK_LENGTH / model.dims.n_audio_ctx  # usually 0.02 seconds
            max_initial_timestamp_index = None
            if options.max_initial_timestamp:
                max_initial_timestamp_index = round(
                    self.options.max_initial_timestamp / precision
                )
            self.logit_filters.append(
                ApplyTimestampRules(
                    tokenizer, self.sample_begin, max_initial_timestamp_index
                )
            )