import os import gradio as gr os.system("pip install kantts -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html") os.system("pip install numpy==1.22.0") from modelscope.models.audio.tts import SambertHifigan from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks import IPython.display as ipd 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) def infer(text): output = inference(input=text) with open("myfile.wav", mode='bx') as f: f.write(output["output_wav"]) return "myfile.wav" app = gr.Blocks() with app: gr.HTML("
" "

🥳🎶🎡 - KanTTS中文声音克隆

" "
") gr.Markdown("###
🌊 - 更多精彩应用,敬请关注[滔滔AI](http://www.talktalkai.com);滔滔AI,为爱滔滔!💕
") with gr.Row(): with gr.Column(): inp = gr.Textbox(lines=5, label="请填写您想要转换的中文文本") btn = gr.Button("一键生成") out = gr.Audio(label="为您生成的专属音频", type="filepath") btn.click(fn=infer, inputs=[inp], outputs=[out]) app.launch(show_error=True)