Spaces:
Runtime error
Runtime error
| #Imports--------------------------------------------------------------- | |
| import gradio as gr | |
| import subprocess | |
| import torch | |
| from transformers import pipeline | |
| import os | |
| #User defined functions (UDF) | |
| from functions.charts import spider_chart | |
| from functions.dictionaries import calculate_average, transform_dict | |
| from functions.icon import generate_icon | |
| from functions.timestamp import format_timestamp | |
| from functions.youtube import get_youtube_video_id | |
| #---------------------------------------------------------------------- | |
| MODEL_NAME = "openai/whisper-medium" | |
| #MODEL_NAME = "jpdiazpardo/whisper-tiny-metal" | |
| BATCH_SIZE = 8 | |
| device = 0 if torch.cuda.is_available() else "cpu" | |
| #Transformers pipeline | |
| pipe = pipeline( | |
| task="automatic-speech-recognition", | |
| model=MODEL_NAME, | |
| chunk_length_s=30, | |
| device=device | |
| ) | |
| #Formating--------------------------------------------------------------------------------------------- | |
| title = "Whisper Demo: Transcribe Audio" | |
| description = ("Transcribe long-form audio inputs with the click of a button! Demo uses the" | |
| f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files" | |
| " of arbitrary length. Check some of the 'cool' examples below") | |
| linkedin = generate_icon("linkedin") | |
| github = generate_icon("github") | |
| article = ("<div style='text-align: center; max-width:800px; margin:10px auto;'>" | |
| f"<p>{linkedin} <a href='https://www.linkedin.com/in/juanpablodiazp/' target='_blank'>Juan Pablo Díaz Pardo</a><br>" | |
| f"{github} <a href='https://github.com/jpdiazpardo' target='_blank'>jpdiazpardo</a></p>") | |
| title = "Scream: Fine-Tuned Whisper model for automatic gutural speech recognition 🤟🤟🤟" | |
| examples = [["Whitechapel - Prostatic Fluid Asphyxiation.wav",True,True], | |
| ["Suicide Silence - Genocide.wav",True,True] | |
| ] | |
| #------------------------------------------------------------------------------------------------------------------------------- | |
| #Define classifier for sentiment analysis | |
| classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=None) | |
| #Functions----------------------------------------------------------------------------------------------------------------------- | |
| def transcribe(file,use_timestamps=True,sentiment_analysis=True): | |
| '''inputs: file, return_timestamps''' | |
| outputs = pipe(file, batch_size=BATCH_SIZE, generate_kwargs={"task": 'transcribe'}, return_timestamps=True) | |
| text = outputs["text"] | |
| timestamps = outputs["chunks"] | |
| #If return timestamps is True, return html text with timestamps format | |
| if use_timestamps==True: | |
| spider_text = [f"{chunk['text']}" for chunk in timestamps] #Text for spider chart without timestamps | |
| timestamps = [f"[{format_timestamp(chunk['timestamp'][0])} -> {format_timestamp(chunk['timestamp'][1])}] {chunk['text']}" for chunk in timestamps] | |
| else: | |
| timestamps = [f"{chunk['text']}" for chunk in timestamps] | |
| spider_text = timestamps | |
| text = "<br>".join(str(feature) for feature in timestamps) | |
| text = f"<h4>Transcription</h4><div style='overflow-y: scroll; height: 150px;'>{text}</div>" | |
| spider_text = "\n".join(str(feature) for feature in spider_text) | |
| trans_dict=[transform_dict(classifier.predict(t)[0]) for t in spider_text.split("\n")] | |
| av_dict = calculate_average(trans_dict) | |
| fig = spider_chart(av_dict) | |
| return text, fig, av_dict | |
| embed_html = '<iframe src="https://www.youtube.com/embed/YOUTUBE_ID'\ | |
| 'title="YouTube video player" frameborder="0" allow="accelerometer;'\ | |
| 'autoplay; clipboard-write; encrypted-media; gyroscope;'\ | |
| 'picture-in-picture" allowfullscreen></iframe>' | |
| def download(link): | |
| '''Runs youtubetowav.py | |
| inputs: link from textbox''' | |
| subprocess.run(['python3', 'youtubetowav.py', link]) | |
| return thumbnail.update(value=embed_html.replace("YOUTUBE_ID",get_youtube_video_id(link))) | |
| def hide_sentiment(value): | |
| if value == True: | |
| return sentiment_plot.update(visible=True), sentiment_frequency.update(visible=True) | |
| else: | |
| return sentiment_plot.update(visible=False), sentiment_frequency.update(visible=False) | |
| #---------------------------------------------------------------------------------------------------------------------------------------------- | |
| #Components------------------------------------------------------------------------------------------------------------------------------------ | |
| #Input components | |
| #yt_link = gr.Textbox(value=None,label="YouTube link", info = "Optional: Copy and paste YouTube URL") #0 | |
| #download_button = gr.Button(value="Download") #1 | |
| #thumbnail = gr.HTML(value="", label = "Thumbnail") #2 | |
| audio_input = gr.Audio(source="upload", type="filepath", label="Upload audio file for transcription") #3 | |
| timestamp_checkbox = gr.Checkbox(value=True, label="Return timestamps") #4 | |
| sentiment_checkbox = gr.Checkbox(value=True, label="Sentiment analysis") #5 | |
| inputs = [audio_input, #0 | |
| timestamp_checkbox, #1 | |
| sentiment_checkbox] #2 | |
| #Ouput components | |
| #audio_out = gr.Audio(label="Processed Audio", type="filepath", info = "Vocals only") | |
| sentiment_plot = gr.Plot(label="Sentiment Analysis") | |
| sentiment_frequency = gr.Label(label="Frequency") | |
| outputs = [gr.outputs.HTML("text"), sentiment_plot, sentiment_frequency] | |
| #---------------------------------------------------------------------------------------------------------------------------------------------------- | |
| #Launch demo----------------------------------------------------------------------------------------------------------------------------------------- | |
| with gr.Blocks() as demo: | |
| #download_button.click(download, inputs=[yt_link], outputs=[thumbnail]) | |
| sentiment_checkbox.change(hide_sentiment, inputs=[sentiment_checkbox], outputs=[sentiment_plot, sentiment_frequency]) | |
| with gr.Column(): | |
| gr.Interface(title = title, fn=transcribe, inputs = inputs, outputs = outputs, | |
| description=description, cache_examples=True, allow_flagging="never", article = article, | |
| examples=examples) | |
| demo.queue(concurrency_count=3) | |
| demo.launch(debug = True) | |
| #---------------------------------------------------------------------------------------------------------------------------------------------------- |