app_locally.py

import os
import torch
import argparse
import gradio as gr
#from zipfile import ZipFile
from melo.api import TTS

# Init EN/ZH baseTTS and ToneConvertor
from openVoice import se_extractor
from openVoice.api import ToneColorConverter
import devicetorch

device = devicetorch.get(torch)

ckpt_converter = 'checkpoints/converter'
tone_color_converter = ToneColorConverter(f'{ckpt_converter}/config.json', device=device)
tone_color_converter.load_ckpt(f'{ckpt_converter}/checkpoint.pth')

def predict(prompt, style, audio_file_pth, mic_file_path, use_mic, language):
    # initialize a empty info
    text_hint = ''

    tts_model = TTS(language=language, device=device)
    speaker_id = models[language].hps.data.spk2id
    speaker_key = speaker_key.lower().replace('_', '-')
    source_se = torch.load(f'checkpoints/base_speakers/ses/{speaker_key}.pth', map_location=device)


    if use_mic == True:
        if mic_file_path is not None:
            speaker_wav = mic_file_path
        else:
            text_hint += f"[ERROR] Please record your voice with Microphone, or uncheck Use Microphone to use reference audios\n"
            gr.Warning(
                "Please record your voice with Microphone, or uncheck Use Microphone to use reference audios"
            )
            return (
                text_hint,
                None,
                None,
            )

    else:
        speaker_wav = audio_file_pth

    if len(prompt) < 2:
        text_hint += f"[ERROR] Please give a longer prompt text \n"
        gr.Warning("Please give a longer prompt text")
        return (
            text_hint,
            None,
            None,
        )
    
    # note diffusion_conditioning not used on hifigan (default mode), it will be empty but need to pass it to model.inference
    try:
        target_se, wavs_folder = se_extractor.get_se(speaker_wav, tone_color_converter, target_dir='processed', max_length=60., vad=True)
        # os.system(f'rm -rf {wavs_folder}')
    except Exception as e:
        text_hint += f"[ERROR] Get target tone color error {str(e)} \n"
        gr.Warning(
            "[ERROR] Get target tone color error {str(e)} \n"
        )
        return (
            text_hint,
            None,
            None,
        )

    src_path = f'{output_dir}/tmp.wav'

    speed = 1.0

    tts_model.tts(prompt, src_path, speaker=style, language=language)

    save_path = f'{output_dir}/output.wav'
    # Run the tone color converter
    encode_message = "@MyShell"
    tone_color_converter.convert(
        audio_src_path=src_path, 
        src_se=source_se, 
        tgt_se=target_se, 
        output_path=save_path,
        message=encode_message)

    text_hint += f'''Get response successfully \n'''

    return (
        text_hint,
        save_path,
        speaker_wav,
    )


examples = [
    [
        "今天天气真好，我们一起出去吃饭吧。",
        'default',
        "examples/speaker0.mp3",
        None,
        False,
        True,
    ],[
        "This audio is generated by open voice with a half-performance model.",
        'whispering',
        "examples/speaker1.mp3",
        None,
        False,
        True,
    ],
    [
        "He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.",
        'sad',
        "examples/speaker2.mp3",
        None,
        False,
        True,
    ],
]

with gr.Blocks(analytics_enabled=False) as demo:

#    with gr.Row():
#        gr.HTML(wrapped_markdown_content)

    with gr.Row():
        with gr.Column():
            input_text_gr = gr.Textbox(
                label="Text Prompt",
                info="One or two sentences at a time is better. Up to 200 text characters.",
                value="He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.",
            )
            style_gr = gr.Dropdown(
                label="Style",
                info="Select a style of output audio for the synthesised speech. (Chinese only support 'default' now)",
                choices=['default', 'whispering', 'cheerful', 'terrified', 'angry', 'sad', 'friendly'],
                max_choices=1,
                value="default",
            )
            ref_gr = gr.Audio(
                label="Reference Audio",
                info="Click on the ✎ button to upload your own target speaker audio",
                type="filepath",
                value="examples/speaker0.mp3",
            )
            mic_gr = gr.Audio(
                source="microphone",
                type="filepath",
                info="Use your microphone to record audio",
                label="Use Microphone for Reference",
            )
            use_mic_gr = gr.Checkbox(
                label="Use Microphone",
                value=False,
                info="Notice: Microphone input may not work properly under traffic",
            )
            language = gr.Radio(['EN_NEWEST', 'EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN_NEWEST')

            tts_button = gr.Button("Send", elem_id="send-btn", visible=True)


        with gr.Column():
            out_text_gr = gr.Text(label="Info")
            audio_gr = gr.Audio(label="Synthesised Audio", autoplay=True)
            ref_audio_gr = gr.Audio(label="Reference Audio Used")

            gr.Examples(examples,
                        label="Examples",
                        inputs=[input_text_gr, style_gr, ref_gr, mic_gr, use_mic_gr, language],
                        outputs=[out_text_gr, audio_gr, ref_audio_gr],
                        fn=predict,
                        cache_examples=False,)
            tts_button.click(predict, [input_text_gr, style_gr, ref_gr, mic_gr, use_mic_gr, language], outputs=[out_text_gr, audio_gr, ref_audio_gr])

demo.queue()  
demo.launch(debug=True, show_api=True)