Update app.py

app.py

@@ -29,53 +29,18 @@ def transcribe(inputs, task):
     if inputs is None:
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
 
-    result = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)
-    text = result["text"]
-    timestamps = result["chunks"]
-
-    timestamp_str = "\n".join([f"[{chunk['timestamp']}] {chunk['text']}" for chunk in timestamps])
-    
-    return text, timestamp_str
-
-
-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()
+    result = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps="word")
     
-    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.")
+    text = result["text"]
+    timestamps = result["chunks"]  # each chunk contains the word and its timestamps
     
-    ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
+    word_timestamps = []
+    for chunk in timestamps:
+        for word_info in chunk["words"]:
+            word_timestamps.append(f"{word_info['word']} [{word_info['start']}-{word_info['end']}]")
     
-    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))
+    return "\n".join(word_timestamps)
+
 
 @spaces.GPU
 def yt_transcribe(yt_url, task, max_filesize=75.0):
@@ -90,13 +55,18 @@ def yt_transcribe(yt_url, task, max_filesize=75.0):
     inputs = ffmpeg_read(inputs, pipe.feature_extractor.sampling_rate)
     inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
 
-    result = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)
+    result = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps="word")
+    
     text = result["text"]
     timestamps = result["chunks"]
 
-    timestamp_str = "\n".join([f"[{chunk['timestamp']}] {chunk['text']}" for chunk in timestamps])
+    word_timestamps = []
+    for chunk in timestamps:
+        for word_info in chunk["words"]:
+            word_timestamps.append(f"{word_info['word']} [{word_info['start']}-{word_info['end']}]")
     
-    return html_embed_str, text, timestamp_str
+    return html_embed_str, "\n".join(word_timestamps)
+
 
 
 demo = gr.Blocks()