Spaces:
Build error
Build error
| import whisper | |
| from pytube import YouTube | |
| from transformers import pipeline | |
| import gradio as gr | |
| import os | |
| import re | |
| model = whisper.load_model("base") | |
| # model = pipeline(model="AlexMo/FIFA_WC22_WINNER_LANGUAGE_MODEL") | |
| summarizer = pipeline("summarization") | |
| def transcribe(microphone, file_upload): | |
| warn_output = "" | |
| if (microphone is not None) and (file_upload is not None): | |
| warn_output = ( | |
| "WARNING: You've uploaded an audio file and used the microphone. " | |
| "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n" | |
| ) | |
| elif (microphone is None) and (file_upload is None): | |
| return "ERROR: You have to either use the microphone or upload an audio file" | |
| file = microphone if microphone is not None else file_upload | |
| text = summarizer(file)["text"] | |
| return warn_output + text | |
| def getAudio(url): | |
| link = YouTube(url) | |
| video = link.streams.filter(only_audio=True).first() | |
| file = video.download(output_path=".") | |
| base, ext = os.path.splitext(file) | |
| file_ext = base + '.mp3' | |
| os.rename(file, file_ext) | |
| return file_ext | |
| def getText(url): | |
| if url != '': | |
| output_text_transcribe = '' | |
| res = model.transcribe(getAudio(url)) | |
| return res['text'].strip() | |
| def getSummary(article): | |
| header = ' '.join(re.split(r'(?<=[.:;])\s', article)[:5]) | |
| b = summarizer(header, min_length=15, max_length=120, do_sample=False) | |
| b = b[0]['summary_text'].replace(' .', '.').strip() | |
| return b | |
| mf_transcribe = gr.Interface( | |
| fn=transcribe, | |
| inputs=[ | |
| gr.inputs.Audio(source="microphone", type="filepath", optional=True), | |
| gr.inputs.Audio(source="upload", type="filepath", optional=True), | |
| ], | |
| outputs="text", | |
| layout="horizontal", | |
| theme="huggingface", | |
| title="Dutch whisper summarizer", | |
| description=( | |
| "Get a transcription and summary of some Dutch audio input!." | |
| ), | |
| allow_flagging="never", | |
| ) | |
| with gr.Blocks() as demo: | |
| gr.HTML( | |
| """ | |
| <div style="text-align: center; max-width: 500px; margin: 0 auto;"> | |
| <div> | |
| <h1>Dutch whisperer</h1> | |
| </div> | |
| <p style="margin-bottom: 10px; font-size: 94%"> | |
| Summarize audio files, mic input or Youtube videos using OpenAI's Whisper | |
| </p> | |
| </div> | |
| """ | |
| ) | |
| with gr.Tab('Get a summary from your own mic or audio file'): | |
| mf_transcribe | |
| with gr.Tab('Summary of Youtube video'): | |
| input_text_url = gr.Textbox(placeholder='Youtube video URL', label='URL') | |
| result_button_transcribe = gr.Button('1. Transcribe') | |
| output_text_transcribe = gr.Textbox(placeholder='Transcript of the YouTube video.', label='Transcript') | |
| result_button_summary = gr.Button('2. Create Summary') | |
| output_text_summary = gr.Textbox(placeholder='Summary of the YouTube video transcript.', label='Summary') | |
| result_button_transcribe.click(getText, inputs=input_text_url, outputs=output_text_transcribe) | |
| result_button_summary.click(getSummary, inputs=output_text_transcribe, outputs=output_text_summary) | |
| demo.launch(debug=True) |