AnswerToSpeech
Use this node in question-answering pipelines to convert text Answers into SpeechAnswers. The answer and its context are read out into two audio files.
This node is experimental because of the data classes it uses (SpeechAnswer). Bear in mind that they might change in the future.
| Position in a Pipeline | The last node in the pipeline, after a Reader |
| Input | Answer |
| Output | SpeechAnswer |
| Classes | AnswerToSpeech |
Usage
To initialize AnswerToSpeech, run:
from haystack.nodes import AnswerToSpeech
model_name = 'espnet/kan-bayashi_ljspeech_vits'
answer_dir = './generated_audio_answers'
audio_answer = AnswerToSpeech(model_name_or_path=model_name, generated_audio_dir=answer_dir)
To use AnswerToSpeech in a pipeline, run:
from haystack.nodes import AnswerToSpeech
retriever = BM25Retriever(document_store=document_store)
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)
answer2speech = AnswerToSpeech(
model_name_or_path="espnet/kan-bayashi_ljspeech_vits",
generated_audio_dir=Path(__file__).parent / "audio_answers",
)
audio_pipeline = Pipeline()
audio_pipeline.add_node(retriever, name="Retriever", inputs=["Query"])
audio_pipeline.add_node(reader, name="Reader", inputs=["Retriever"])
audio_pipeline.add_node(answer2speech, name="AnswerToSpeech", inputs=["Reader"])
Updated about 1 year ago