Add basic ASR demo app with t-tech/T-one model

app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import torch
+from transformers import pipeline
+
+# Load the ASR model
+# Using the t-tech/T-one model for automatic speech recognition
+asr_pipeline = pipeline(
+    "automatic-speech-recognition",
+    model="t-tech/T-one",
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device=0 if torch.cuda.is_available() else -1
+)
+
+def transcribe_audio(audio_file):
+    """
+    Transcribe audio file using the T-one ASR model
+    Args:
+        audio_file: Audio file uploaded by user
+    Returns:
+        str: Transcribed text
+    """
+    if audio_file is None:
+        return "Please upload an audio file."
+    
+    try:
+        # Transcribe the audio
+        result = asr_pipeline(audio_file)
+        return result["text"]
+    except Exception as e:
+        return f"Error during transcription: {str(e)}"
+
+# Create Gradio interface
+with gr.Blocks(title="T-one ASR Demo") as demo:
+    gr.Markdown("# T-one Automatic Speech Recognition Demo")
+    gr.Markdown("Upload an audio file to get real-time transcription using the t-tech/T-one model.")
+    
+    with gr.Row():
+        # Audio input component
+        audio_input = gr.Audio(
+            label="Upload Audio File",
+            type="filepath"
+        )
+        
+        # Text output component
+        text_output = gr.Textbox(
+            label="Transcription",
+            placeholder="Transcribed text will appear here...",
+            lines=5
+        )
+    
+    # Set up the transcription function to run when audio is uploaded
+    audio_input.change(
+        fn=transcribe_audio,
+        inputs=audio_input,
+        outputs=text_output
+    )
+
+# Launch the app
+if __name__ == "__main__":
+    demo.launch()