Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+import tensorflow as tf
+from transformers import Wav2Vec2Processor, TFWav2Vec2Model
+import librosa
+
+# Load the model and processor
+processor = Wav2Vec2Processor.from_pretrained("openai/whisper-tiny")
+model = TFWav2Vec2Model.from_pretrained("kobrasoft/kobraspeech-rnn-cs")
+
+def transcribe(audio):
+    # Load audio
+    audio, rate = librosa.load(audio, sr=16000)
+    
+    # Process audio
+    inputs = processor(audio, sampling_rate=rate, return_tensors="tf", padding="longest")
+    logits = model(inputs.input_values).logits
+    
+    # Decode the logits
+    predicted_ids = tf.argmax(logits, axis=-1)
+    transcription = processor.batch_decode(predicted_ids)[0]
+    return transcription
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.inputs.Audio(source="microphone", type="filepath"),
+    outputs="text",
+    title="ASR Model Demo",
+    description="Upload an audio file or record your voice to get the transcription."
+)
+
+if __name__ == "__main__":
+    iface.launch()