Create app.py

app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+import torch
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import torchaudio
+
+model_id = "facebook/wav2vec2-large-960h-lv60-self"
+
+processor = Wav2Vec2Processor.from_pretrained(model_id)
+model = Wav2Vec2ForCTC.from_pretrained(model_id)
+
+def transcribe(audio):
+    waveform, sample_rate = torchaudio.load(audio)
+    if sample_rate != 16000:
+        resampler = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)
+        waveform = resampler(waveform)
+    input_values = processor(waveform.squeeze(), return_tensors="pt", sampling_rate=16000).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
+
+demo = gr.Interface(fn=transcribe, inputs=gr.Audio(type="filepath"), outputs="text")
+demo.launch()