def _main_loop()

in whisper/decoding.py [0:0]

• 21 lines of code
• 9 McCabe index (conditional complexity)

    def _main_loop(self, audio_features: Tensor, tokens: Tensor):
        n_batch = tokens.shape[0]
        sum_logprobs: Tensor = torch.zeros(n_batch, device=audio_features.device)
        no_speech_probs = [np.nan] * n_batch

        try:
            for i in range(self.sample_len):
                logits = self.inference.logits(tokens, audio_features)

                if (
                    i == 0 and self.tokenizer.no_speech is not None
                ):  # save no_speech_probs
                    probs_at_sot = logits[:, self.sot_index].float().softmax(dim=-1)
                    no_speech_probs = probs_at_sot[:, self.tokenizer.no_speech].tolist()

                # now we need to consider the logits at the last token only
                logits = logits[:, -1]

                # apply the logit filters, e.g. for suppressing or applying penalty to
                for logit_filter in self.logit_filters:
                    logit_filter.apply(logits, tokens)

                # expand the tokens tensor with the selected next tokens
                tokens, completed = self.decoder.update(tokens, logits, sum_logprobs)

                if completed or tokens.shape[-1] > self.n_ctx:
                    break
        finally:
            self.inference.cleanup_caching()

        return tokens, sum_logprobs, no_speech_probs