paddlespeech.cli.tts.infer module

class paddlespeech.cli.tts.infer.TTSExecutor

Bases: BaseExecutor

Methods

disable_task_loggers()	Disable all loggers in current task.
execute(argv)	Command line entry.
get_input_source(input_)	Get task input source from command line input.
infer(text[, lang, am, spk_id])	Model inference and result stored in self.output.
postprocess([output])	Output postprocess and return results.
postprocess_onnx([output])	Output postprocess and return results.
preprocess(input, *args, **kwargs)	Input preprocess and return paddle.Tensor stored in self._inputs.
process_task_results(input_, results[, ...])	Handling task results and redirect stdout if needed.
show_rtf(info)	Calculate rft of current task and show results.

__call__
infer_onnx

execute(argv: List[str]) → bool

Command line entry.

infer(text: str, lang: str = 'zh', am: str = 'fastspeech2_csmsc', spk_id: int = 0)

Model inference and result stored in self.output.

infer_onnx(text: str, lang: str = 'zh', am: str = 'fastspeech2_csmsc', spk_id: int = 0)

postprocess(output: str = 'output.wav') → Union[str, PathLike]

Output postprocess and return results. This method get model output from self._outputs and convert it into human-readable results.

Returns:

Union[str, os.PathLike]: Human-readable results such as texts and audio files.

postprocess_onnx(output: str = 'output.wav') → Union[str, PathLike]

Output postprocess and return results. This method get model output from self._outputs and convert it into human-readable results.

Returns:

Union[str, os.PathLike]: Human-readable results such as texts and audio files.

preprocess(input: Any, *args, **kwargs)

Input preprocess and return paddle.Tensor stored in self._inputs. Input content can be a text(tts), a file(asr, cls), a stream(not supported yet) or anything needed.

Args:

input (Any): Input text/file/stream or other content.