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

from modelscope.models.audio.tts import SambertHifigan
import os
import time

model_dir = "/home/gpu/KAN-TTS/pretrain_work_dir/"

custom_infer_abs = {
'voice_name':
'F7',
'am_ckpt':
os.path.join(model_dir, 'tmp_am', 'ckpt'),
'am_config':
os.path.join(model_dir, 'tmp_am', 'config.yaml'),
'voc_ckpt':
os.path.join(model_dir, 'orig_model', 'basemodel_16k', 'hifigan', 'ckpt'),
'voc_config':
os.path.join(model_dir, 'orig_model', 'basemodel_16k', 'hifigan',
'config.yaml'),
'audio_config':
os.path.join(model_dir, 'data', 'audio_config.yaml'),
'se_file':
os.path.join(model_dir, 'data', 'se', 'se.npy')
}
kwargs = {'custom_ckpt': custom_infer_abs}

model_id = SambertHifigan(os.path.join(model_dir, "orig_model"), **kwargs)

sambert_hifigan_tts = pipeline(task=Tasks.text_to_speech, model=model_id)

output = sambert_hifigan_tts(input=text)

wav = output[OutputKeys.OUTPUT_WAV]

with open('output.wav', 'wb') as f:
f.write(wav)

========================>
尝试用

不知道为什么，KAN-TTS，按如上SSML格式，设置了不同的语速,得到的语速是一样的。与不设置rate参数得到的，语速没有区别。用Audacity看时长也一致 (pretrain_work_dir中是自己训练的模型，听声音内容是正确的)。