def _get_sample()

in ultravox/data/datasets.py [0:0]

• 35 lines of code
• 3 McCabe index (conditional complexity)

    def _get_sample(self, row) -> Optional[data_sample.VoiceSample]:
        assert self._config.user_template is not None
        assert self._config.user_template_args is not None
        assert self._config.assistant_template is not None
        assert self._config.transcript_template is not None
        try:
            user_content = jinja2.Template(
                self._config.user_template, undefined=jinja2.StrictUndefined
            ).render(
                **row,
                text_proc=text_proc,
                **self._config.user_template_args,
            )
            assistant_content = jinja2.Template(
                self._config.assistant_template, undefined=jinja2.StrictUndefined
            ).render(**row, text_proc=text_proc)
            transcript = jinja2.Template(
                self._config.transcript_template, undefined=jinja2.StrictUndefined
            ).render(**row, text_proc=text_proc)
        except jinja2.TemplateError as e:
            print(f"Error rendering template: {e}")
            print(f"user_template: {self._config.user_template}")
            print(f"assistant_template: {self._config.assistant_template}")
            print(f"transcript_template: {self._config.transcript_template}")
            print(f"sample keys: {list(row.keys())}")
            raise ValueError(
                "Template rendering failed. Make sure all keys in the template exist in the sample."
            ) from e
        if not self._args.include_audio:
            user_content = user_content.replace(
                types.AUDIO_PLACEHOLDER, f'"{transcript}"'
            )
        messages = _get_messages(user_content, assistant_content)
        audio = self._get_audio(row, self._config.audio_field)
        return self._make_sample(messages, audio, audio_transcript=transcript)