语音情感合成

from scipy.io.wavfile import write

from modelscope.outputs import OutputKeys from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks

text = '待合成文本' model_id = 'damo/speech_sambert-hifigan_tts_zhizhe_emo_zh-cn_16k' sambert_hifigan_tts = pipeline(task=Tasks.text_to_speech, model=model_id) output = sambert_hifigan_tts(input=text) pcm = output[OutputKeys.OUTPUT_PCM] write('output.wav', 16000, pcm)

使用modelscope时如何传入情感标签，我按照源码的参数传入，好像不起作用 output = sambert_hifigan_tts(input=text， inputs_emotion=5)

请参考https://help.aliyun.com/document_detail/101645.html#sectiondiv-g6w-isw-rmw

使用SSML emotion标签即可实现添加情感标签。