Update app.py

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import torch
+from transformers import pipeline
+from timeit import default_timer as timer
+
+username = "fmagot01"  ## Complete your username
+model_id = f"{username}/distil-wav2vec2-finetuned-giga-speech"
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+pipe = pipeline("audio-classification", model=model_id, device=device)
+
+# def predict_trunc(filepath):
+#     preprocessed = pipe.preprocess(filepath)
+#     truncated = pipe.feature_extractor.pad(preprocessed,truncation=True, max_length = 16_000*30)
+#     model_outputs = pipe.forward(truncated)
+#     outputs = pipe.postprocess(model_outputs)
+
+#     return outputs
+
+
+def classify_audio(filepath):
+    """
+      Goes from
+      [{'score': 0.8339303731918335, 'label': 'Gaming'},
+    {'score': 0.11914275586605072, 'label': 'Audiobook'},]
+     to
+     {"Gaming":  0.8339303731918335, "Audiobook":0.11914275586605072}
+    """
+    start_time = timer()
+    preds = pipe(filepath)
+    # preds = predict_trunc(filepath)
+    outputs = {}
+    pred_time = round(timer() - start_time, 5)
+    for p in preds:
+        outputs[p["label"]] = p["score"]
+    return outputs, pred_time
+    #return outputs
+
+
+title = "Classifier of Music Genres"
+description = """
+This is the demo of the finetuned classification model that we just trained on the [GTZAN](https://huggingface.co/datasets/marsyas/gtzan). You can upload your own audio file or used the ones already provided below.
+"""
+
+filenames = ['TAINY_88_melodic_loop_keys_las_Emin.wav', "TAINY_92_melodic_loop_keys_lam_Ebmin.wav", "TunePocket-Lively-Polka-Dance-30-Sec-Preview.mp3"]
+filenames = [[f"./{f}"] for f in filenames]
+demo = gr.Interface(
+    fn=classify_audio,
+    inputs=gr.Audio(type="filepath"),
+    outputs=[gr.outputs.Label(label="Predictions"),
+             gr.Number(label="Prediction time (s)")
+            ],
+    title=title,
+    description=description,
+    examples=filenames,
+)
+demo.launch()