Update app.py

app.py

@@ -1,16 +1,18 @@
 import torch
+
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
+
 import tempfile
 import os
-import time
 
-# Model and setup
 MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
-YT_LENGTH_LIMIT_S = 3600  # 1-hour limit for YouTube files
+FILE_LIMIT_MB = 1000
+YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
+
 device = 0 if torch.cuda.is_available() else "cpu"
 
 pipe = pipeline(
@@ -20,34 +22,74 @@ pipe = pipeline(
     device=device,
 )
 
-# Function to transcribe audio
+
 def transcribe(inputs, task):
     if inputs is None:
-        raise gr.Error("No audio file submitted! Please upload or record an audio file.")
+        raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
+
     text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
-    return text
+    return  text
+
 
-# YouTube video processing functions
 def _return_yt_html_embed(yt_url):
     video_id = yt_url.split("?v=")[-1]
-    return f'<center><iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"></iframe></center>'
+    HTML_str = (
+        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
+        " </center>"
+    )
+    return HTML_str
 
 def download_yt_audio(yt_url, filename):
-    # [ ... existing code for download_yt_audio ... ]
+    info_loader = youtube_dl.YoutubeDL()
+    
+    try:
+        info = info_loader.extract_info(yt_url, download=False)
+    except youtube_dl.utils.DownloadError as err:
+        raise gr.Error(str(err))
+    
+    file_length = info["duration_string"]
+    file_h_m_s = file_length.split(":")
+    file_h_m_s = [int(sub_length) for sub_length in file_h_m_s]
+    
+    if len(file_h_m_s) == 1:
+        file_h_m_s.insert(0, 0)
+    if len(file_h_m_s) == 2:
+        file_h_m_s.insert(0, 0)
+    file_length_s = file_h_m_s[0] * 3600 + file_h_m_s[1] * 60 + file_h_m_s[2]
+    
+    if file_length_s > YT_LENGTH_LIMIT_S:
+        yt_length_limit_hms = time.strftime("%HH:%MM:%SS", time.gmtime(YT_LENGTH_LIMIT_S))
+        file_length_hms = time.strftime("%HH:%MM:%SS", time.gmtime(file_length_s))
+        raise gr.Error(f"Maximum YouTube length is {yt_length_limit_hms}, got {file_length_hms} YouTube video.")
+    
+    ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
+    
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        try:
+            ydl.download([yt_url])
+        except youtube_dl.utils.ExtractorError as err:
+            raise gr.Error(str(err))
 
-def yt_transcribe(yt_url, task):
+
+def yt_transcribe(yt_url, task, max_filesize=75.0):
     html_embed_str = _return_yt_html_embed(yt_url)
+
     with tempfile.TemporaryDirectory() as tmpdirname:
         filepath = os.path.join(tmpdirname, "video.mp4")
         download_yt_audio(yt_url, filepath)
         with open(filepath, "rb") as f:
             inputs = f.read()
+
     inputs = ffmpeg_read(inputs, pipe.feature_extractor.sampling_rate)
     inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
+
     text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+
     return html_embed_str, text
 
-# Gradio interfaces
+
+demo = gr.Blocks()
+
 mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
@@ -58,7 +100,12 @@ mf_transcribe = gr.Interface(
     layout="horizontal",
     theme="huggingface",
     title="Whisper Large V3: Transcribe Audio",
-    description="Transcribe long-form microphone or audio inputs with the click of a button!"
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
+        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
+        " of arbitrary length."
+    ),
+    allow_flagging="never",
 )
 
 file_transcribe = gr.Interface(
@@ -69,9 +116,14 @@ file_transcribe = gr.Interface(
     ],
     outputs="text",
     layout="horizontal",
-    theme="NoCrypt/miku@1.2.1",
+    theme="huggingface",
     title="Whisper Large V3: Transcribe Audio",
-    description="Transcribe long-form microphone or audio inputs with the click of a button!"
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
+        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
+        " of arbitrary length."
+    ),
+    allow_flagging="never",
 )
 
 yt_transcribe = gr.Interface(
@@ -82,16 +134,18 @@ yt_transcribe = gr.Interface(
     ],
     outputs=["html", "text"],
     layout="horizontal",
-    theme="NoCrypt/miku@1.2.1",
+    theme="huggingface",
     title="Whisper Large V3: Transcribe YouTube",
-    description="Transcribe long-form YouTube videos with the click of a button!"
+    description=(
+        "Transcribe long-form YouTube videos with the click of a button! Demo uses the checkpoint"
+        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
+        " arbitrary length."
+    ),
+    allow_flagging="never",
 )
 
-# Main Gradio application
-with gr.Blocks(theme="NoCrypt/miku@1.2.1") as demo:     
-    gr.HTML("<h1><center>AI Assistant<h1><center>")
+with demo:
     gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
 
 demo.launch(enable_queue=True)
 
-