File size: 3,136 Bytes
356bab3 5cd1d6b 1487f7e 93d849e 949b582 4041d63 5cd1d6b a952e20 4041d63 a952e20 1487f7e 4041d63 1487f7e 5cd1d6b 3c10179 1487f7e 5cd1d6b beed497 5cd1d6b 042492f 5cd1d6b 356bab3 4041d63 cf392a0 4041d63 f430f55 cf392a0 4041d63 beed497 4041d63 f430f55 cf392a0 4041d63 beed497 5cd1d6b 1487f7e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
import gradio as gr
import os
from moviepy.editor import VideoFileClip
from transformers import pipeline
# Load models
asr = pipeline(task="automatic-speech-recognition", model="distil-whisper/distil-small.en")
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
stored_transcript = ""
def transcribe_and_summarize(video_file):
global stored_transcript
if video_file is None:
return "Error: No file provided.", ""
try:
video = VideoFileClip(video_file)
audio_path = "temp_audio.wav"
video.audio.write_audiofile(audio_path, codec='pcm_s16le')
transcription_result = asr(audio_path, return_timestamps=True)
transcribed_text = " ".join([segment['text'] for segment in transcription_result['chunks']])
stored_transcript = transcribed_text
if len(transcribed_text.split()) < 50:
summarized_text = "Text too short to summarize."
else:
summary_result = summarizer(transcribed_text, max_length=500, min_length=100, do_sample=False)
summarized_text = summary_result[0]['summary_text']
return transcribed_text, summarized_text
except Exception as e:
return f"Error: {str(e)}", ""
def answer_question(question):
global stored_transcript
if not stored_transcript:
return "Please transcribe a video first."
result = qa_pipeline(question=question, context=stored_transcript)
return result['answer']
with gr.Blocks(css="""
body { background-color: black !important; }
.gradio-container { color: #FFFF33 !important; }
button { background-color: #FFFF33 !important; color: black !important; border: none !important; }
input, textarea, .gr-textbox, .gr-video { background-color: #111 !important; color: #FFFF33 !important; border-color: #FFFF33 !important; }
""") as iface:
gr.HTML("<h1 style='color:#FFFF33'>🎥 Video Transcriber, Summarizer & Q&A Tool</h1>")
gr.HTML("<p style='color:#CCCC33'>Upload a video to get a transcript, summary, and ask questions about its content.</p>")
with gr.Tab("📝 Transcription & Summary"):
video_input = gr.Video(label="Upload Video (.mp4)", interactive=True)
transcribe_btn = gr.Button("🚀 Transcribe and Summarize")
transcribed_text = gr.Textbox(label="Transcribed Text", lines=8, interactive=False)
summarized_text = gr.Textbox(label="Summarized Text", lines=8, interactive=False)
transcribe_btn.click(fn=transcribe_and_summarize, inputs=video_input, outputs=[transcribed_text, summarized_text])
with gr.Tab("❓ Ask Questions"):
question_input = gr.Textbox(label="Ask a question based on the transcript", placeholder="E.g., What is the main topic?")
ask_btn = gr.Button("🔍 Get Answer")
answer_output = gr.Textbox(label="Answer", interactive=False)
ask_btn.click(fn=answer_question, inputs=question_input, outputs=answer_output)
# Launch app
port = int(os.environ.get('PORT1', 7860))
iface.launch(share=True, server_port=port)
|