Update app.py

app.py

@@ -3,22 +3,61 @@ import os
 import time
 import sys
 import subprocess
+import tempfile
+import requests
+from urllib.parse import urlparse
 
 # Clone and install faster-whisper from GitHub
 subprocess.run(["git", "clone", "https://github.com/SYSTRAN/faster-whisper.git"], check=True)
 subprocess.run(["pip", "install", "-e", "./faster-whisper"], check=True)
+subprocess.run(["pip", "install", "yt-dlp"], check=True)
 
 # Add the faster-whisper directory to the Python path
 sys.path.append("./faster-whisper")
 
 from faster_whisper import WhisperModel
 from faster_whisper.transcribe import BatchedInferencePipeline
+import yt_dlp
 
-def transcribe_audio(audio_path, batch_size):
+def download_audio(url):
+    parsed_url = urlparse(url)
+    if parsed_url.netloc == 'www.youtube.com' or parsed_url.netloc == 'youtu.be':
+        # YouTube video
+        ydl_opts = {
+            'format': 'bestaudio/best',
+            'postprocessors': [{
+                'key': 'FFmpegExtractAudio',
+                'preferredcodec': 'mp3',
+                'preferredquality': '192',
+            }],
+            'outtmpl': '%(id)s.%(ext)s',
+        }
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(url, download=True)
+            return f"{info['id']}.mp3"
+    else:
+        # Direct MP3 URL
+        response = requests.get(url)
+        if response.status_code == 200:
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
+                temp_file.write(response.content)
+                return temp_file.name
+        else:
+            raise Exception(f"Failed to download audio from {url}")
+
+def transcribe_audio(input_source, batch_size):
     # Initialize the model
     model = WhisperModel("cstr/whisper-large-v3-turbo-int8_float32", device="auto", compute_type="int8")
     batched_model = BatchedInferencePipeline(model=model)
 
+    # Handle input source
+    if isinstance(input_source, str) and (input_source.startswith('http://') or input_source.startswith('https://')):
+        # It's a URL, download the audio
+        audio_path = download_audio(input_source)
+    else:
+        # It's a local file path
+        audio_path = input_source
+
     # Benchmark transcription time
     start_time = time.time()
     segments, info = batched_model.transcribe(audio_path, batch_size=batch_size)
@@ -42,19 +81,27 @@ def transcribe_audio(audio_path, batch_size):
     output += f"Real-time factor: {real_time_factor:.2f}x\n"
     output += f"Audio file size: {audio_file_size:.2f} MB"
 
+    # Clean up downloaded file if it was a URL
+    if isinstance(input_source, str) and (input_source.startswith('http://') or input_source.startswith('https://')):
+        os.remove(audio_path)
+
     return output
 
 # Gradio interface
 iface = gr.Interface(
     fn=transcribe_audio,
     inputs=[
-        gr.Audio(type="filepath", label="Upload Audio File"),
+        gr.inputs.Textbox(label="Audio Source (Upload, MP3 URL, or YouTube URL)"),
         gr.Slider(minimum=1, maximum=32, step=1, value=16, label="Batch Size")
     ],
     outputs=gr.Textbox(label="Transcription and Metrics"),
-    title="Faster Whisper Transcription",
-    description="Upload an audio file to transcribe using Faster Whisper v3 turbo int8. Adjust the batch size for performance tuning.",
-    examples=[["path/to/example/audio.mp3", 16]],
+    title="Faster Whisper v3 turbo int8 transcription",
+    description="Enter an audio file path, MP3 URL, or YouTube URL to transcribe using Faster Whisper v3 turbo (int8). Adjust the batch size for performance tuning.",
+    examples=[
+        ["https://www.youtube.com/watch?v=dQw4w9WgXcQ", 16],
+        ["https://example.com/path/to/audio.mp3", 16],
+        ["path/to/local/audio.mp3", 16]
+    ],
 )
 
 iface.launch()