import os
from modelscope.models.audio.tts import SambertHifigan
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

model_dir = os.path.abspath("./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)

inference = pipeline(task=Tasks.text_to_speech, model=model_id)
output = inference(input="今天的天气真不错")

import IPython.display as ipd
ipd.Audio(output["output_wav"], rate=16000)