Duplicate from juanpy/videoresumen

Co-authored-by: Juan OP <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: VideoSummary
+emoji: 📚
+colorFrom: blue
+colorTo: gray
+sdk: gradio
+sdk_version: 3.16.0
+app_file: app.py
+pinned: true
+duplicated_from: juanpy/videoresumen
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,63 @@
+from tempfile import TemporaryDirectory
+from typing import List
+
+from pytube import YouTube
+import whisper
+from transformers import pipeline
+import gradio as gr
+
+
+def get_title(url: str) -> str:
+    """Returns the title of the YouTube video at the given URL."""
+    yt = YouTube(url)
+    return f"**{yt.title}**"
+
+
+def download_audio(url: str, path: str) -> None:
+    """Downloads the audio from the YouTube video at the given URL and saves it to the specified path."""
+    yt = YouTube(url)
+    audio = yt.streams.filter(only_audio=True).first()
+    audio.download(output_path=path, filename="a.mp4")
+
+
+def transcribe(path: str) -> List[str]:
+    """Transcribes the audio file at the given path and returns the text."""
+    model = whisper.load_model("tiny")
+    transcription = model.transcribe(path, fp16=False)["text"]
+    transcription_chunks = [transcription[i : i + 1000] for i in range(0, len(transcription), 1000)]
+    return transcription_chunks
+
+
+def summarize(transcription: List[str]) -> str:
+    """Summarizes the given text and returns the summary."""
+    model = pipeline("summarization", model="facebook/bart-large-cnn")
+    summary_chunks = model(transcription, max_length=80, min_length=30)
+    summary = (" ".join([chunks["summary_text"] for chunks in summary_chunks]).strip().replace(" . ", ". "))
+    return summary
+
+
+def execute_pipeline(url: str) -> str:
+    """Generates a temporary directory and executes the pipeline to download, transcribe and summarize the video."""
+    with TemporaryDirectory(dir=".") as tmp_dir:
+        download_audio(url, tmp_dir)
+        result = transcribe(f"{tmp_dir}/a.mp4")
+        text = summarize(result)
+        return text
+
+
+def main() -> None:
+    """Generates the Gradio interface."""
+    with gr.Blocks(analytics_enabled=True, title="Summarize a video") as page:
+        gr.HTML('<h2 style="text-align:center"><span style="font-size:36px">Summarize a <strong>Youtube</strong> video</span></h2>')
+        url = gr.Textbox(label="Enter the URL:")
+        title = gr.Markdown()
+        output = gr.Textbox(label="Summary")
+        summarize_btn = gr.Button("Go!").style(full_width=False)
+        summarize_btn.click(fn=get_title, inputs=url, outputs=title)
+        summarize_btn.click(fn=execute_pipeline, inputs=url, outputs=output)
+        gr.Markdown("*Works best with videos under 10 minutes. It usually takes around 2-3 minutes to execute.*")
+    page.launch()
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,5 @@
+gradio==3.16.0
+pytube==12.1.2
+transformers==4.25.1
+whisper @ git+https://github.com/openai/whisper.git@28769fcfe50755a817ab922a7bc83483159600a9
+