Create app.py

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+import torch
+import numpy as np
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+from scipy.signal import resample
+
+# Load model and processor
+model_id = "facebook/wav2vec2-large-960h-lv60-self"
+processor = Wav2Vec2Processor.from_pretrained(model_id)
+model = Wav2Vec2ForCTC.from_pretrained(model_id)
+
+# Transcription function
+def transcribe(audio, sample_rate):
+    if audio is None:
+        return "⚠️ No audio received."
+
+    # Resample if needed
+    if sample_rate != 16000:
+        number_of_samples = round(len(audio) * 16000 / sample_rate)
+        audio = resample(audio, number_of_samples)
+
+    # Process and predict
+    input_values = processor(audio, sampling_rate=16000, return_tensors="pt").input_values
+    with torch.no_grad():
+        logits = model(input_values).logits
+        predicted_ids = torch.argmax(logits, dim=-1)
+        transcription = processor.batch_decode(predicted_ids)[0]
+
+    return transcription.lower()
+
+# Launch UI
+demo = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(sources=["microphone"], type="numpy", label="🎤 Speak now"),
+    outputs=gr.Textbox(label="📝 Transcription"),
+    title="Wav2Vec2 Speech Transcription",
+    description="Speak into the microphone and get a transcription using Wav2Vec2 (Hugging Face)."
+)
+
+demo.launch()