Update app.py

app.py

@@ -2,15 +2,16 @@ import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
+import torch
 
 import tempfile
 import os
-import time  # Hinzugefügtes Modul für die Zeitberechnung
+import time
 
 MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
 FILE_LIMIT_MB = 1000
-YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
+YT_LENGTH_LIMIT_S = 3600
 
 device = 0 if torch.cuda.is_available() else "cpu"
 
@@ -26,18 +27,68 @@ def transcribe(inputs, task):
         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
 
-# ... (Fortsetzung des Codes für die Funktionen _return_yt_html_embed, download_yt_audio, yt_transcribe, etc.)
+def _return_yt_html_embed(yt_url):
+    video_id = yt_url.split("?v=")[-1]
+    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):
+    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, 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
 
-# Schritt 1: Definiere das gr.Blocks-Element für das Layout der Demo
 demo = gr.Blocks(theme="TogetherAi/Alex2")
 
-# Schritt 2: Ändere das Layout für das Blockelement auf "centered" und setze die Breite auf 500 Pixel
-demo.layout = "centered"  # Layout auf "centered" ändern
-demo.width = 500  # Breite auf 500 setzen
+demo.layout = "centered"
+demo.width = 500
 
-# Schritt 3: Erstelle die Schnittstellen wie zuvor für Audioaufnahmen, das Hochladen von Audiodateien und das Transkribieren von YouTube-Videos
 mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
@@ -78,7 +129,7 @@ yt_transcribe = gr.Interface(
     fn=yt_transcribe,
     inputs=[
         gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
+        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe")
     ],
     outputs=["html", "text"],
     layout="horizontal",
@@ -92,10 +143,7 @@ yt_transcribe = gr.Interface(
     allow_flagging="never",
 )
 
-# Schritt 4: Erstelle eine TabbedInterface, um die verschiedenen Schnittstellen für Mikrofon, Hochladen von Audiodateien und YouTube-Transkription anzuzeigen
 with demo:
     gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
 
-# Schritt 5: Starte die Demo
 demo.launch(enable_queue=True)
-