import gradio as gr from typing import Any import torch from transformers import pipeline from diffusers import StableDiffusionPipeline from TTS.api import TTS import whisper import utils from youtubeaudioextractor import PytubeAudioExtractor from transcriber import SpanishTranscriber, WhisperTranscriber from textprocessor import TextProcessor from videocreator import VideoCreator spanish_transcribe_model = "juancopi81/whisper-medium-es" languages = {"Spanish": "es", "English": "en"} device = "cuda" if torch.cuda.is_available() else "cpu" device_dict = {"cuda": 0, "cpu": -1} dtype = torch.float16 if device == "cuda" else torch.float32 # Detect if code is running in Colab is_colab = utils.is_google_colab() colab_instruction = "" if is_colab else """
You can skip the queue using Colab:
""" device_print = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶" # Initialize components audio_extractor = PytubeAudioExtractor() es_transcription_pipe = pipeline( task="automatic-speech-recognition", model=spanish_transcribe_model, chunk_length_s=30, device=device_dict[device], ) es_transcription_pipe.model.config.forced_decoder_ids = es_transcription_pipe.tokenizer.get_decoder_prompt_ids(language="es", task="transcribe") es_audio_transcriber = SpanishTranscriber(es_transcription_pipe) en_transcription_pipe = whisper.load_model("base") en_audio_transcriber = WhisperTranscriber(en_transcription_pipe) openai_model = "text-davinci-003" text_processor = TextProcessor(openai_model) image_model_id = "runwayml/stable-diffusion-v1-5" image_pipeline = StableDiffusionPipeline.from_pretrained(image_model_id, torch_dtype=dtype, revision="fp16") image_pipeline = image_pipeline.to(device) es_vo_model_name = TTS.list_models()[22] en_vo_model_name = TTS.list_models()[8] # Init TTS es_tts = TTS(es_vo_model_name) en_tts = TTS(en_vo_model_name) def datapipeline(url: str, video_language: str, summary_language: str, video_styles: str) -> Any: audio_path_file = audio_extractor.extract(url) print(f"Audio file created at: {audio_path_file}") # Select transcriber if video_language == "Spanish": audio_transcriber = es_audio_transcriber video_creator = VideoCreator(es_tts, image_pipeline) elif video_language == "English": audio_transcriber = en_audio_transcriber video_creator = VideoCreator(en_tts, image_pipeline) else: return "Language not supported" transcribed_text = audio_transcriber.transcribe(audio_path_file) print("Audio transcription ready!") json_scenes = text_processor.get_json_scenes(transcribed_text, summary_language) print("Scenes ready") video = video_creator.create_video(json_scenes, video_styles) print("Video at", video) return video, video css = """ a { color: inherit; text-decoration: underline; } .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: #000000; background: #000000; } input[type='range'] { accent-color: #000000; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 730px; margin: auto; padding-top: 1.5rem; } #gallery { min-height: 22rem; margin-bottom: 15px; margin-left: auto; margin-right: auto; border-bottom-right-radius: .5rem !important; border-bottom-left-radius: .5rem !important; } #gallery>div>.h-full { min-height: 20rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } #advanced-btn { font-size: .7rem !important; line-height: 19px; margin-top: 12px; margin-bottom: 12px; padding: 2px 8px; border-radius: 14px !important; } #advanced-options { margin-bottom: 20px; } .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .acknowledgments h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } #container-advanced-btns{ display: flex; flex-wrap: wrap; justify-content: space-between; align-items: center; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important; } #share-btn * { all: unset; } .gr-form{ flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0; } #prompt-container{ gap: 0; } #generated_id{ min-height: 700px } #setting_id{ margin-bottom: 12px; text-align: center; font-weight: 900; } """ block = gr.Blocks(css=css) with block as demo: gr.HTML( f"""Enter the URL of a YouTube video (in Spanish) and you'll recive a video with an illustraded summary. It works for audio books, history lessons, etc. Try it out with a short video (less than 4 minutes).
Running on {device_print}
Some samples videos you can try: