Spaces:
Runtime error
Runtime error
| import os, sys | |
| import uuid | |
| import tempfile | |
| import pyttsx3 | |
| import gradio as gr | |
| from src.gradio_demo import SadTalker | |
| # from src.utils.text2speech import TTSTalker | |
| from huggingface_hub import snapshot_download | |
| def get_source_image(image): | |
| return image | |
| try: | |
| import webui # in webui | |
| in_webui = True | |
| except: | |
| in_webui = False | |
| def toggle_audio_file(choice): | |
| if choice == False: | |
| return gr.update(visible=True), gr.update(visible=False) | |
| else: | |
| return gr.update(visible=False), gr.update(visible=True) | |
| def ref_video_fn(path_of_ref_video): | |
| if path_of_ref_video is not None: | |
| return gr.update(value=True) | |
| else: | |
| return gr.update(value=False) | |
| def download_model(): | |
| REPO_ID = 'vinthony/SadTalker-V002rc' | |
| snapshot_download(REPO_ID) | |
| # language : en_US, de_DE, ... | |
| # gender : VoiceGenderFemale, VoiceGenderMale | |
| def change_voice(engine, language='ru_ru', gender='male'): | |
| selected_voices = [] | |
| language = language.lower() if language else '' | |
| gender = gender.lower() if gender else '' | |
| for voice in engine.getProperty('voices'): | |
| voice_appended = False | |
| for lang in voice.languages: | |
| lang_str = str(lang, 'utf-8') | |
| print("lang", lang_str) | |
| if lang_str and language in lang_str.lower(): | |
| selected_voices.append(voice) | |
| print("voice appended by lang", voice, lang_str) | |
| voice_appended = True | |
| break | |
| if voice_appended: | |
| continue | |
| if voice.id and language in voice.id.lower(): | |
| selected_voices.append(voice) | |
| print("voice appended by id", voice.id) | |
| continue | |
| if voice.name and language in voice.name.lower(): | |
| selected_voices.append(voice) | |
| print("voice appended by name", voice.name) | |
| continue | |
| for voice in selected_voices: | |
| if voice.gender and gender in voice.gender.lower(): | |
| engine.setProperty('voice', voice.id) | |
| print("voice selected by gender", voice.gender) | |
| return True | |
| if voice.id and gender in voice.id.lower(): | |
| engine.setProperty('voice', voice.id) | |
| print("voice selected by id", voice.id) | |
| return True | |
| if voice.name and gender in voice.name.lower(): | |
| engine.setProperty('voice', voice.id) | |
| print("voice selected by name", voice.name) | |
| return True | |
| if len(selected_voices) > 0: | |
| engine.setProperty('voice', selected_voices[0].id) | |
| print("voice selected by default", selected_voices[0].id) | |
| return True | |
| return False | |
| def play_text_to_speech(text_input, voice_option): | |
| engine = pyttsx3.init() | |
| change_voice(engine, 'ru', voice_option) | |
| print("text_input", text_input) | |
| print("voice_option", voice_option) | |
| time_tag = str(uuid.uuid4()) | |
| save_dir = './results/voice_input' | |
| os.makedirs(save_dir, exist_ok=True) | |
| file_name = os.path.join(save_dir, os.path.basename(time_tag + '.wav')) | |
| open(file_name, "wb").close() | |
| engine.say(text_input) | |
| engine.save_to_file(text_input, file_name) | |
| engine.runAndWait() | |
| print("file saved to", file_name) | |
| return file_name | |
| def sadtalker_demo(): | |
| download_model() | |
| sad_talker = SadTalker(lazy_load=True) | |
| # tts_talker = TTSTalker() | |
| with gr.Blocks(analytics_enabled=False) as sadtalker_interface: | |
| with gr.Row(): | |
| with gr.Column(variant='panel'): | |
| with gr.Tabs(elem_id="sadtalker_source_image"): | |
| with gr.TabItem('Source image'): | |
| with gr.Row(): | |
| source_image = gr.Image(label="Source image", source="upload", type="filepath", elem_id="img2img_image") | |
| with gr.Tabs(elem_id="sadtalker_driven_audio"): | |
| with gr.TabItem('Driving Methods'): | |
| with gr.Row(): | |
| driven_audio = gr.Audio(label="Input audio", source="upload", type="filepath") | |
| driven_audio_no = gr.Audio(label="Use IDLE mode, no audio is required", source="upload", type="filepath", visible=False) | |
| with gr.Column(visible=False): | |
| use_idle_mode = gr.Checkbox(label="Use Idle Animation", visible=False) | |
| length_of_audio = gr.Number(value=5, label="The length(seconds) of the generated video.") | |
| use_idle_mode.change(toggle_audio_file, inputs=use_idle_mode, outputs=[driven_audio, driven_audio_no]) # todo | |
| with gr.Row(): | |
| text_input = gr.Textbox(label="Enter text", multiline=True) | |
| voice_option = gr.Radio(['Male', 'Female'], label='Voice Option', value='Female') | |
| with gr.Row(): | |
| play_button = gr.Button('Text To Speech', variant='primary') | |
| play_button.click( | |
| fn=play_text_to_speech, | |
| inputs=[text_input, voice_option], | |
| outputs=[driven_audio] | |
| ) | |
| with gr.Row(): | |
| ref_video = gr.Video(label="Reference Video", source="upload", type="filepath", elem_id="vidref") | |
| with gr.Column(): | |
| use_ref_video = gr.Checkbox(label="Use Reference Video") | |
| ref_info = gr.Radio(['pose', 'blink','pose+blink', 'all'], value='pose', label='Reference Video',info="How to borrow from reference Video?((fully transfer, aka, video driving mode))") | |
| ref_video.change(ref_video_fn, inputs=ref_video, outputs=[use_ref_video]) # todo | |
| with gr.Column(variant='panel'): | |
| with gr.Tabs(elem_id="sadtalker_checkbox"): | |
| with gr.TabItem('Settings'): | |
| with gr.Column(variant='panel'): | |
| # width = gr.Slider(minimum=64, elem_id="img2img_width", maximum=2048, step=8, label="Manually Crop Width", value=512) # img2img_width | |
| # height = gr.Slider(minimum=64, elem_id="img2img_height", maximum=2048, step=8, label="Manually Crop Height", value=512) # img2img_width | |
| with gr.Row(): | |
| pose_style = gr.Slider(minimum=0, maximum=45, step=1, label="Pose style", value=0) # | |
| exp_weight = gr.Slider(minimum=0, maximum=3, step=0.1, label="expression scale", value=1) # | |
| blink_every = gr.Checkbox(label="use eye blink", value=True) | |
| with gr.Row(): | |
| size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?") # | |
| preprocess_type = gr.Radio(['crop', 'resize','full', 'extcrop', 'extfull'], value='crop', label='preprocess', info="How to handle input image?") | |
| with gr.Row(): | |
| is_still_mode = gr.Checkbox(label="Still Mode (fewer head motion, works with preprocess `full`)") | |
| facerender = gr.Radio(['facevid2vid','pirender'], value='facevid2vid', label='facerender', info="which face render?") | |
| with gr.Row(): | |
| batch_size = gr.Slider(label="batch size in generation", step=1, maximum=10, value=1) | |
| enhancer = gr.Checkbox(label="GFPGAN as Face enhancer") | |
| submit = gr.Button('Generate', elem_id="sadtalker_generate", variant='primary') | |
| with gr.Tabs(elem_id="sadtalker_genearted"): | |
| gen_video = gr.Video(label="Generated video", format="mp4") | |
| submit.click( | |
| fn=sad_talker.test, | |
| inputs=[source_image, | |
| driven_audio, | |
| preprocess_type, | |
| is_still_mode, | |
| enhancer, | |
| batch_size, | |
| size_of_image, | |
| pose_style, | |
| facerender, | |
| exp_weight, | |
| use_ref_video, | |
| ref_video, | |
| ref_info, | |
| use_idle_mode, | |
| length_of_audio, | |
| blink_every | |
| ], | |
| outputs=[gen_video] | |
| ) | |
| return sadtalker_interface | |
| if __name__ == "__main__": | |
| demo = sadtalker_demo() | |
| demo.queue(max_size=10) | |
| demo.launch(debug=True) | |