Update app.py

app.py

@@ -1,150 +1,106 @@
-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
-
-MODEL_NAME = "chiyo123/whisper-small-tonga"
-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 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
-
+import torch
 
-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>"
+# Initialize the speech recognition pipeline
+print("Loading Whisper Lozi model...")
+try:
+    # Use the specific Lozi model
+    transcriber = pipeline(
+        "automatic-speech-recognition",
+        model="simzacademy/whisper-small-lozi1",
+        device=0 if torch.cuda.is_available() else -1  # Use GPU if available
     )
-    return HTML_str
-
-def download_yt_audio(yt_url, filename):
-    info_loader = youtube_dl.YoutubeDL()
+    print("Model loaded successfully!")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    transcriber = None
+
+def transcribe_audio(audio):
+    """
+    Transcribe audio to text using the Whisper Lozi model
     
-    try:
-        info = info_loader.extract_info(yt_url, download=False)
-    except youtube_dl.utils.DownloadError as err:
-        raise gr.Error(str(err))
+    Args:
+        audio: Audio file path or tuple (sample_rate, audio_data)
     
-    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]
+    Returns:
+        Transcribed text
+    """
+    if transcriber is None:
+        return "Error: Model failed to load. Please check your installation."
     
-    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 audio is None:
+        return "Please provide an audio file or recording."
     
-    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.")
+    try:
+        # Transcribe the audio
+        result = transcriber(audio)
+        return result["text"]
+    except Exception as e:
+        return f"Error during transcription: {str(e)}"
+
+# Create the Gradio interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        # 🎤 Lozi Speech-to-Text Interface
+        ### Powered by Whisper Small Lozi Model
+        
+        This interface uses the `simzacademy/whisper-small-lozi1` model to transcribe 
+        Lozi language speech to text.
+        """
+    )
     
-    ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
+    with gr.Row():
+        with gr.Column():
+            # Audio input - supports both recording and file upload
+            audio_input = gr.Audio(
+                sources=["microphone", "upload"],
+                type="filepath",
+                label="Record or Upload Audio"
+            )
+            
+            transcribe_btn = gr.Button("🔄 Transcribe", variant="primary", size="lg")
+        
+        with gr.Column():
+            output_text = gr.Textbox(
+                label="Transcription",
+                placeholder="Your transcription will appear here...",
+                lines=10
+            )
     
-    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
-
-
-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="chiyo123/whisper-small-tonga",
-    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",
-)
-
-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 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.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")
-    ],
-    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."
-    ),
-    allow_flagging="never",
-)
-
-with demo:
-    gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
+    gr.Markdown(
+        """
+        ### 📋 Instructions:
+        1. **Record**: Click the microphone icon to record audio directly
+        2. **Upload**: Or click to upload an audio file (MP3, WAV, etc.)
+        3. **Transcribe**: Click the "Transcribe" button to convert speech to text
+        4. **View**: The transcribed text will appear on the right
+        
+        ### ℹ️ Notes:
+        - Speak clearly in Lozi for best results
+        - The model works best with clear audio and minimal background noise
+        - First transcription may take longer as the model loads
+        """
+    )
+    
+    # Set up the transcription action
+    transcribe_btn.click(
+        fn=transcribe_audio,
+        inputs=audio_input,
+        outputs=output_text
+    )
+    
+    # Also allow Enter key to trigger transcription
+    audio_input.change(
+        fn=lambda: gr.update(interactive=True),
+        outputs=transcribe_btn
+    )
 
-demo.launch(enable_queue=True)
+# Launch the interface
+if __name__ == "__main__":
+    demo.launch(
+        share=False,  # Set to True to create a public link
+        server_name="0.0.0.0",  # Allow access from network
+        server_port=7860
+    )