complete

app.py

@@ -1,93 +1,50 @@
 import torch
+import time
 
 import gradio as gr
 import spaces
-import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
 
-import tempfile
-import os
+DEFAULT_MODEL_NAME = "openai/whisper-tiny"
 
-MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
-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,
-    chunk_length_s=30,
-    device=device,
-)
+def load_pipeline(model_name):
+    return pipeline(
+        task="automatic-speech-recognition",
+        model=model_name,
+        chunk_length_s=30,
+        device=device,
+    )
+
+pipe = load_pipeline(DEFAULT_MODEL_NAME)
 
 @spaces.GPU
-def transcribe(inputs, task):
+def transcribe(inputs, task, model_name):
     if inputs is None:
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
 
+    global pipe
+    if model_name != pipe.model.name_or_path:
+        pipe = load_pipeline(model_name)
+
+    start_time = time.time()  # Record the start time
     text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
-    return  text
+    end_time = time.time()  # Record the end time
 
+    transcription_time = end_time - start_time  # Calculate the transcription time
 
-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>"
+    # Create the transcription time output with additional information
+    transcription_time_output = (
+        f"Transcription Time: {transcription_time:.2f} seconds\n"
+        f"Model Used: {model_name}\n"
+        f"Device Used: {'GPU' if torch.cuda.is_available() else 'CPU'}"
     )
-    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
 
+    return text, transcription_time_output
 
 demo = gr.Blocks()
 
@@ -96,14 +53,19 @@ mf_transcribe = gr.Interface(
     inputs=[
         gr.Audio(type="filepath"),
         gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
+        gr.Textbox(
+            label="Model Name",
+            value=DEFAULT_MODEL_NAME,
+            placeholder="Enter the model name",
+            info="Some available models: distil-whisper/distil-large-v3 distil-whisper/distil-medium.en   Systran/faster-distil-whisper-large-v3 Systran/faster-whisper-large-v3  Systran/faster-whisper-medium    openai/whisper-tiny , openai/whisper-base, openai/whisper-medium, openai/whisper-large-v3"
+        ),
     ],
-    outputs="text",
+    outputs=[gr.TextArea(label="Transcription"), gr.TextArea(label="Transcription Info")],
     theme="huggingface",
-    title="Whisper Large V3: Transcribe Audio",
+    title="Whisper Transcription",
     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."
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the specified OpenAI Whisper"
+        " checkpoint and 🤗 Transformers to transcribe audio files of arbitrary length."
     ),
     allow_flagging="never",
 )
@@ -113,37 +75,24 @@ file_transcribe = gr.Interface(
     inputs=[
         gr.Audio(type="filepath", label="Audio file"),
         gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
+        gr.Textbox(
+            label="Model Name",
+            value=DEFAULT_MODEL_NAME,
+            placeholder="Enter the model name",
+            info="Some available models: openai/whisper-tiny, openai/whisper-base, openai/whisper-medium, openai/whisper-large-v2"
+        ),
     ],
-    outputs="text",
-    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."
-    ),
-    allow_flagging="never",
-)
-
-yt_transcribe = 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=[gr.TextArea(label="Transcription"), gr.TextArea(label="Transcription Info")],
     theme="huggingface",
-    title="Whisper Large V3: Transcribe YouTube",
+    title="Whisper Transcription",
     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."
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the specified OpenAI Whisper"
+        " checkpoint and 🤗 Transformers to transcribe audio files of arbitrary length."
     ),
     allow_flagging="never",
 )
 
 with demo:
-    gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
-
-demo.launch()
+    gr.TabbedInterface([mf_transcribe, file_transcribe], ["Microphone", "Audio file"])
 
+demo.launch(share=True)

requirements.txt

@@ -1,3 +1,4 @@
 git+https://github.com/huggingface/transformers
 torch
 yt-dlp
+gradio==4.8.0