Duplicate from darthPanda/youtube-video-to-text-generation

Co-authored-by: Taaha Saleem Bajwa <[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: Youtube Video To Text Generation
+emoji: 📊
+colorFrom: indigo
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.19.0
+app_file: app.py
+pinned: false
+duplicated_from: darthPanda/youtube-video-to-text-generation
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,75 @@
+import streamlit as st
+import requests
+import re
+import openai
+from pytube import YouTube
+import os
+
+# Remove previous audio file
+audio_filename = "temp.mp3"
+if os.path.exists(audio_filename):
+    os.remove(audio_filename)
+
+# Function to check if the provided OpenAI API key is valid
+def is_valid_openai_key(api_key):
+    try:
+        openai.api_key = api_key
+        openai.Engine.list()
+        return True
+    except Exception as e:
+        st.write(f"Error: {e}")
+        return False
+
+# Function to check if a provided link is a valid YouTube video link
+def is_valid_youtube_link(url):
+    youtube_regex = re.compile(
+        r'(https?://)?(www\.)?'
+        r'(youtube|youtu|youtube-nocookie)\.(com|be)/'
+        r'(watch\?v=|embed/|v/|.+\?v=)?([^&=%\?]{11})'
+    )
+    return youtube_regex.match(url) is not None
+
+# Define the application layout
+st.set_page_config(page_title="YouTube Video to Text", layout="wide")
+
+# Add the application header
+st.title("YouTube Video to Text")
+
+# Add the side panel
+with st.sidebar:
+    st.header("Settings")
+    openai_api_key = st.text_input("OpenAI API Key", type="password")
+    youtube_video_link = st.text_input("YouTube Video Link")
+    st.caption('Note: Only videos in english language are currently supported.')
+
+# In the main section of the app, add the following code:
+if openai_api_key and youtube_video_link and is_valid_youtube_link(youtube_video_link):
+    if is_valid_openai_key(openai_api_key):
+        # Your code to process the YouTube video using the OpenAI API goes here
+        print(youtube_video_link)
+        youtube_video = YouTube(youtube_video_link, use_oauth=True, allow_oauth_cache=True)
+        st.markdown(f"Title: **{youtube_video.title}**")
+        streams=youtube_video.streams.filter(only_audio=True)
+        stream=streams.last()
+        with st.spinner('Downloading Audio'):
+            stream.download(filename='temp.mp3')
+        audio_file= open("temp.mp3", "rb")
+        with st.spinner('Transcribing Text'):
+            transcript_json = openai.Audio.transcribe("whisper-1", audio_file)
+            transcript = transcript_json["text"]
+            st.markdown("**Text:**")
+            st.markdown(transcript)
+    else:
+        st.warning("Invalid OpenAI API Key. Please enter a valid API key.")
+else:
+    st.warning("Please enter a valid YouTube video link and OpenAI API key.")
+
+# Add the footer with the creator's name and GitHub link
+st.markdown(
+    """
+    <div style="position: fixed; bottom: 10px; right: 10px; width: auto; height: auto; background-color: white; border: 1px solid #f0f2f6; border-radius: 5px; padding: 1rem;">
+        Created by Taaha Bajwa - <a href="https://github.com/yourusername/yourrepository" target="_blank">Source Code</a>
+    </div>
+    """,
+    unsafe_allow_html=True
+)

requirements.txt

@@ -0,0 +1,3 @@
+streamlit==1.17.0
+openai
+pytube