Update app.py

update to use dataset

app.py

@@ -1,136 +1,87 @@
-import spaces
-import torch
-
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
-
+from huggingface_hub import CommitScheduler
 import tempfile
 import os
+import json
+from datetime import datetime
+from pathlib import Path
+from uuid import uuid4
 
 MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
-FILE_LIMIT_MB = 1000
-YT_LENGTH_LIMIT_S = 4800  # limit to 1.5 hour YouTube files
+YT_LENGTH_LIMIT_S = 4800  # 1 hour limit
 
 device = 0 if torch.cuda.is_available() else "cpu"
+pipe = pipeline(task="automatic-speech-recognition", model=MODEL_NAME, chunk_length_s=30, device=device)
 
-pipe = pipeline(
-    task="automatic-speech-recognition",
-    model=MODEL_NAME,
-    chunk_length_s=30,
-    device=device,
-)
+JSON_DATASET_DIR = Path("json_dataset")
+JSON_DATASET_DIR.mkdir(parents=True, exist_ok=True)
+JSON_DATASET_PATH = JSON_DATASET_DIR / f"transcriptions-{uuid4()}.json"
 
+scheduler = CommitScheduler(
+    repo_id="your-dataset-repo",
+    repo_type="dataset",
+    folder_path=JSON_DATASET_DIR,
+    path_in_repo="data",
+)
 
-@spaces.GPU(duration=120)
-def transcribe(inputs, task):
+def transcribe_audio(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
+    return text
 
 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]
-    
+    file_h_m_s = list(map(int, file_length.split(":")))
     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]
-    
+    file_length_s = sum(x * 60 ** i for i, x in enumerate(reversed(file_h_m_s)))
     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"}
-    
+    ydl_opts = {"outtmpl": filename, "format": "bestaudio/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))
-
-@spaces.GPU(duration=120)
-def yt_transcribe(yt_url, task, max_filesize=75.0):
-    html_embed_str = _return_yt_html_embed(yt_url)
+        ydl.download([yt_url])
 
+def yt_transcribe(yt_url, task):
     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"]
+    save_transcription(yt_url, text)
+    return text
 
-    return html_embed_str, text
-
+def save_transcription(yt_url, transcription):
+    with scheduler.lock:
+        with JSON_DATASET_PATH.open("a") as f:
+            json.dump({"url": yt_url, "transcription": transcription, "datetime": datetime.now().isoformat()}, f)
+            f.write("\n")
 
 demo = gr.Blocks()
 
-mf_transcribe = gr.Interface(
-    fn=transcribe,
-    inputs=[
-        gr.Audio(sources="microphone", type="filepath"),
-        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
-    ],
-    outputs="text",
-    title="Whisper Large V3: 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.Audio(sources="upload", type="filepath", label="Audio file"),
-        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
-    ],
-    outputs="text",
-    title="Whisper Large V3: 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(
+yt_transcribe_interface = gr.Interface(
     fn=yt_transcribe,
     inputs=[
         gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
         gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
     ],
-    outputs=["html", "text"],
+    outputs="text",
     title="Whisper Large V3: Transcribe YouTube",
     description=(
         "Transcribe long-form YouTube videos with the click of a button! Demo uses the checkpoint"
@@ -141,7 +92,6 @@ yt_transcribe = gr.Interface(
 )
 
 with demo:
-    gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
+    gr.TabbedInterface([yt_transcribe_interface], ["YouTube"])
 
 demo.queue().launch()
-