test

README.md

@@ -7,6 +7,9 @@ sdk: gradio
 sdk_version: 6.13.0
 app_file: app.py
 pinned: false
+hf_oauth: true
+hf_oauth_scopes:
+  - inference-api
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -2,21 +2,25 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 
 
-def transcribe_audio(audio_file_path):
-    """Transcribe audio using fal.ai for speed"""
-    client = InferenceClient(provider="auto")
+def transcribe_audio(audio_file_path: str, oauth_token: gr.OAuthToken | None) -> str:
+    """Transcribe audio using Inference Providers, billed to the user."""
+    if oauth_token is None:
+        raise gr.Error("Please sign in with Hugging Face first.")
 
-    # Pass the file path directly - the client handles file reading
+    client = InferenceClient(provider="auto", token=oauth_token.token)
     transcript = client.automatic_speech_recognition(
         audio=audio_file_path,
         model="openai/whisper-large-v3"
     )
-
     return transcript.text
 
-def generate_summary(transcript):
-    """Generate summary using an Inference Provider"""
-    client = InferenceClient(provider="auto")
+
+def generate_summary(transcript: str, oauth_token: gr.OAuthToken | None) -> str:
+    """Generate summary using Inference Providers, billed to the user."""
+    if oauth_token is None:
+        raise gr.Error("Please sign in with Hugging Face first.")
+
+    client = InferenceClient(provider="auto", token=oauth_token.token)
 
     prompt = f"""
     Analyze this meeting transcript and provide:
@@ -37,31 +41,47 @@ def generate_summary(transcript):
         messages=[{"role": "user", "content": prompt}],
         max_tokens=1000
     )
-
     return response.choices[0].message.content
 
 
-def process_meeting_audio(audio_file):
-    """Process uploaded audio file and return transcript + summary"""
+def process_meeting_audio(audio_file, oauth_token: gr.OAuthToken | None):
+    """Process uploaded audio file and return transcript + summary."""
+    if oauth_token is None:
+        raise gr.Error("Please sign in with Hugging Face first.")
+
     if audio_file is None:
-        return "Please upload an audio file.", ""
-
-    # We'll implement the AI logic next
-    return "Transcript will appear here...", "Summary will appear here..."
-
-# Create the Gradio interface
-app = gr.Interface(
-    fn=process_meeting_audio,
-    inputs=gr.Audio(label="Upload Meeting Audio", type="filepath"),
-    outputs=[
-        gr.Textbox(label="Transcript", lines=10),
-        gr.Textbox(label="Summary & Action Items", lines=8)
-    ],
-    title="🎤 AI Meeting Notes",
-    description="Upload an audio file to get an instant transcript and summary with action items."
-)
+        raise gr.Error("Please upload an audio file.")
 
-if __name__ == "__main__":
-    app.launch()
+    transcript = transcribe_audio(audio_file, oauth_token)
+    summary = generate_summary(transcript, oauth_token)
+    return transcript, summary
+
+
+with gr.Blocks() as app:
+    gr.Markdown("# 🎤 AI Meeting Notes")
+    gr.Markdown(
+        "Sign in with your Hugging Face account, then upload a meeting recording "
+        "to get an instant transcript and summary. Inference is billed to your account."
+    )
+
+    gr.LoginButton()
+
+    with gr.Row():
+        audio_input = gr.Audio(label="Upload Meeting Audio", type="filepath")
 
+    with gr.Row():
+        submit_btn = gr.Button("Process", variant="primary")
 
+    with gr.Row():
+        transcript_output = gr.Textbox(label="Transcript", lines=10)
+        summary_output = gr.Textbox(label="Summary & Action Items", lines=10)
+
+    submit_btn.click(
+        fn=process_meeting_audio,
+        inputs=[audio_input],
+        outputs=[transcript_output, summary_output],
+    )
+
+
+if __name__ == "__main__":
+    app.launch()