Updating Space

app.py

@@ -1,64 +1,45 @@
+import re
 import gradio as gr
+from youtube_transcript_api import YouTubeTranscriptApi
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+def get_video_id(youtube_url: str) -> str:
+    """
+    Extract the video ID from a given YouTube URL.
+    """
+    # Typical patterns:
+    #   https://www.youtube.com/watch?v=VIDEO_ID
+    #   https://youtu.be/VIDEO_ID
+    #   https://www.youtube.com/shorts/VIDEO_ID
+    pattern = r"(?:v=|/shorts/|\.be/)([^&\n?#]+)"
+    match = re.search(pattern, youtube_url)
+    if not match:
+        raise ValueError("Could not extract video ID from the provided URL.")
+    return match.group(1)
+
+def fetch_transcript(youtube_url: str) -> str:
+    """
+    Given a YouTube URL, fetch the transcript and return it as a single string.
+    """
+    try:
+        video_id = get_video_id(youtube_url)
+        # Fetch transcript
+        transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
+        # Combine the transcript lines
+        transcript = " ".join([entry["text"] for entry in transcript_data])
+        return transcript
+    except Exception as e:
+        return f"Error fetching transcript: {str(e)}"
+
+demo = gr.Interface(
+    fn=fetch_transcript,
+    inputs=gr.Textbox(label="YouTube URL"),
+    outputs="text",
+    title="YouTube Transcript Fetcher",
+    description="Enter a YouTube link to retrieve its transcript."
 )
 
-
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio==5.12.0
+youtube-transcript-api==0.6.3