Update app.py

app.py

@@ -45,49 +45,59 @@ def _return_yt_html_embed(yt_url):
     )
     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):
-    # yt = pt.YouTube(yt_url) # 用 yt_dlp 代替 pytube
-    ydl = youtube_dl.YoutubeDL({"format": "bestaudio"}) # 创建 yt_dlp 对象
-    info = ydl.extract_info(yt_url, download=False) # 提取视频信息
-    audio_url = info["formats"][0]["url"] # 获取音频链接
     html_embed_str = _return_yt_html_embed(yt_url)
-    # stream = yt.streams.filter(only_audio=True)[0]
-    # stream.download(filename="audio.mp3")
-    ydl.download([audio_url]) # 下载音频文件
-    pipe.model.config.forced_decoder_ids = [
-        [2, transcribe_token_id if task == "transcribe" else translate_token_id]
-    ]
-    text = pipe("audio.mp3", return_timestamps=True)
-    # text = pipe("audio.mp3", return_timestamps=True)["text"]
-    # trans to SRT
-    text = convert_to_srt(text)
+
+    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,return_timestamps=True)    
+    # text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"language":"zh"}, return_timestamps=True)
+    # text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+    # text = pipe("audio.mp3",return_timestamps=True)
+    #trans to SRT
+    text= convert_to_srt(text)
     return html_embed_str, text
 
-# Assuming srt format is a sequence of subtitles with index, time range and text
-def convert_to_srt(input):
-    output = ""
-    index = 1
-    for chunk in input["chunks"]:
-        start, end = chunk["timestamp"]
-        text = chunk["text"]
-        if end is None:
-            end = "None"
-        # Convert seconds to hours:minutes:seconds,milliseconds format
-        start = format_time(start)
-        end = format_time(end)
-        output += f"{index}\n{start} --> {end}\n{text}\n\n"
-        index += 1
-    return output
-
-# Helper function to format time
-def format_time(seconds):
-    if seconds == "None":
-        return seconds
-    hours = int(seconds // 3600)
-    minutes = int((seconds % 3600) // 60)
-    seconds = int(seconds % 60)
-    milliseconds = int((seconds % 1) * 1000)
-    return f"{hours:02}:{minutes:02}:{seconds:02},{milliseconds:03}"
 
 demo = gr.Blocks()
 mf_transcribe = gr.Interface(