Update app.py

app.py

@@ -1,133 +1,37 @@
-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
+from gradio_client import Client
 
-MODEL_NAME = "openai/whisper-large-v2"
-BATCH_SIZE = 8
-FILE_LIMIT_MB = 1000
-YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
+def transcribe_audio(youtube_url: str, task: str = "transcribe", return_timestamps: bool = True, api_name: str = "/predict_2") -> dict:
+    """
+    Transcribe audio from a given YouTube URL using a specified model.
 
-device = 0 if torch.cuda.is_available() else "cpu"
+    Parameters:
+    - youtube_url (str): The YouTube URL to transcribe.
+    - task (str, optional): The task to perform. Default is "transcribe".
+    - return_timestamps (bool, optional): Whether to return timestamps. Default is True.
+    - api_name (str, optional): The API endpoint to use. Default is "/predict_2".
 
-pipe = pipeline(
-    task="automatic-speech-recognition",
-    model=MODEL_NAME,
-    chunk_length_s=30,
-    device=device,
-)
+    Returns:
+    - dict: The transcription result.
+    """
+    client = Client("https://sanchit-gandhi-whisper-jax.hf.space/")
+    result = client.predict(youtube_url, task, return_timestamps, api_name)
+    return result
 
 
-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.")
-
-    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
-    return  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
-
-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
+
+MODEL_NAME = "openai/whisper-large-v2"
 
 
 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"),
-    ],
-    outputs="text",
-    layout="horizontal",
-    theme="huggingface",
-    title="Whisper Large V2: Transcribe Audio",
-    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(
-    fn=transcribe,
-    inputs=[
-        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-    ],
-    outputs="text",
-    layout="horizontal",
-    theme="huggingface",
-    title="Whisper Large V2: Transcribe Audio",
-    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(
-    fn=yt_transcribe,
+    fn=transcribe_audio,
     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")
@@ -145,7 +49,7 @@ yt_transcribe = gr.Interface(
 )
 
 with demo:
-    gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
+    gr.TabbedInterface([yt_transcribe], [ "YouTube"])
 
 demo.launch(enable_queue=True)