connect hf to luxi asr api

app.py

@@ -1,49 +1,30 @@
 import gradio as gr
-from transformers import pipeline
-from faster_whisper import WhisperModel
-import librosa
+import requests
 
-# Load the model
-model = WhisperModel("navidved/faster-gooya-v1", device="cpu", compute_type="int8", local_files_only=False)
+def transcribe_audio(file):
+    # Prepare headers and data
+    headers = {
+        'accept': 'application/json',
+        'Authorization': AUTH_TOKEN,
+    }
+    files = {
+        'file': (file.name, file, 'audio/mpeg'),
+    }
 
-# Define the maximum audio length in seconds
-MAX_AUDIO_LENGTH = 30  # seconds
+    # Send POST request
+    response = requests.post(ASR_API_URL, headers=headers, files=files)
 
-# Define the inference function
-def transcribe_audio(audio):
-    if audio is None:
-        return "No audio file uploaded. Please try again."     
-    results = ""
-    try:
-        audio_data, sr = librosa.load(audio, sr=None)
-        duration = librosa.get_duration(y=audio_data, sr=sr)
+    # Check if response is successful
+    if response.status_code == 200:
+        return response.json().get("transcription", "No transcription returned.")
+    else:
+        return f"Error: {response.status_code}, {response.text}"
 
-        # Check if the audio is longer than the allowed duration
-        if duration > MAX_AUDIO_LENGTH:
-            return f"Audio is too long. Please upload an audio file shorter than {MAX_AUDIO_LENGTH} seconds."
-        
-        # Perform transcription
-        segments, _ = model.transcribe(audio, vad_filter=True)
-        for seg in segments:
-            results += seg.text
-        return results
-    except Exception as e:
-        return f"Error during transcription: {str(e)}"
-
-# Create a Gradio interface for uploading audio or using the microphone
-with gr.Blocks() as interface:
-    gr.Markdown("# Gooya v1 Persian Speech Recognition")
-    gr.Markdown("Upload an audio file or use your microphone to transcribe speech to text.")
-    
-    # Create the input and output components
-    audio_input = gr.Audio(type="filepath", label="Input Audio")
-    output_text = gr.Textbox(label="Transcription")
-    
-    # Add a button to trigger the transcription
-    transcribe_button = gr.Button("Transcribe")
-    
-    # Bind the transcribe_audio function to the button click
-    transcribe_button.click(fn=transcribe_audio, inputs=audio_input, outputs=output_text)
-
-# Launch the Gradio app
-interface.launch()
+# Set up the Gradio interface
+gr.Interface(
+    fn=transcribe_audio,
+    inputs=gr.Audio(source="upload", type="file"),
+    outputs="text",
+    title="Gooya v1 Persian Speech Recognition",
+    description="Upload an audio file in Persian, and this model will transcribe it."
+).launch()