Update app.py

app.py

@@ -14,7 +14,6 @@ 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(
     task="automatic-speech-recognition",
     model=MODEL_NAME,
@@ -23,47 +22,35 @@ pipe = pipeline(
 )
 
 
-def transcribe(inputs, task):
+def transcribe(inputs):
     if inputs is None:
         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 pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": "transcribe"}, return_timestamps=True)["text"]
 
 
 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
+    return f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe> </center>'
 
 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])
@@ -71,81 +58,53 @@ def download_yt_audio(yt_url, filename):
             raise gr.Error(str(err))
 
 
-def yt_transcribe(yt_url, task, max_filesize=75.0):
+def yt_transcribe(yt_url, 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"]
-
+    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": "transcribe"}, return_timestamps=True)["text"]
     return html_embed_str, text
 
 
 demo = gr.Blocks()
-
 mf_transcribe = gr.Interface(
     fn=transcribe,
-    inputs=[
-        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-    ],
+    inputs=[gr.inputs.Audio(source="microphone", type="filepath", optional=True)],
     outputs="text",
     layout="horizontal",
     theme="huggingface",
-    title="Whisper Large V3: Transcribe Audio",
-    description=(
-        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the Japanese Whisper"
-        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
-        " of arbitrary length."
-    ),
+    title=f"Transcribe Audio with {os.path.basename(MODEL_NAME)}",
+    description=f"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the Kotoba-Whisper checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files of arbitrary length.",
     allow_flagging="never",
 )
 
 file_transcribe = gr.Interface(
     fn=transcribe,
-    inputs=[
-        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-    ],
+    inputs=[gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file")],
     outputs="text",
     layout="horizontal",
     theme="huggingface",
-    title="Whisper Large V3: Transcribe Audio",
-    description=(
-        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
-        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
-        " of arbitrary length."
-    ),
+    title=f"Transcribe Audio with {os.path.basename(MODEL_NAME)}",
+    description=f"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses Kotoba-Whisper checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files of arbitrary length.",
     allow_flagging="never",
 )
-
 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")
-    ],
+    inputs=[gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")],
     outputs=["html", "text"],
     layout="horizontal",
     theme="huggingface",
-    title="Whisper Large V3: Transcribe YouTube",
-    description=(
-        "Transcribe long-form YouTube videos with the click of a button! Demo uses the OpenAI Whisper checkpoint"
-        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
-        " arbitrary length."
-    ),
+    title=f"Transcribe YouTube with {os.path.basename(MODEL_NAME)}",
+    description=f"Transcribe long-form YouTube videos with the click of a button! Demo uses Kotoba-Whisper checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of arbitrary length.",
     allow_flagging="never",
 )
 
 with demo:
     gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
 
-demo.launch(enable_queue=True)
-
+demo.launch(enable_queue=True)