Update app.py

app.py

@@ -1,49 +1,49 @@
-import gradio as gr
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import torchaudio
-from transformers import AutoConfig, Wav2Vec2FeatureExtractor, Wav2Vec2ForSpeechClassification
-
-import librosa
-import IPython.display as ipd
-import numpy as np
-import pandas as pd
-
-
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model_name_or_path = "m3hrdadfi/wav2vec2-base-100k-voxpopuli-gtzan-music"
-config = AutoConfig.from_pretrained(model_name_or_path)
-feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
-sampling_rate = feature_extractor.sampling_rate
-model = Wav2Vec2ForSpeechClassification.from_pretrained(model_name_or_path).to(device)
-
-
-def speech_file_to_array_fn(path, sampling_rate):
-    speech_array, _sampling_rate = torchaudio.load(path)
-    resampler = torchaudio.transforms.Resample(_sampling_rate)
-    speech = resampler(speech_array).squeeze().numpy()
-    return speech
-
-
-def predict(path, sampling_rate):
-    speech = speech_file_to_array_fn(path, sampling_rate)
-    inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
-    inputs = {key: inputs[key].to(device) for key in inputs}
-
-    with torch.no_grad():
-        logits = model(**inputs).logits
-
-    scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
-    outputs = [{"Label": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
-    return outputs
-
-
-path = "La Campanella.mp3"
-outputs = predict(path, sampling_rate)
-
-
-iface = gr.Interface(fn=predict, inputs=path, outputs=predict(path, sampling_rate))
-iface.launch()
+import gradio as gr
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchaudio
+from transformers import AutoConfig, Wav2Vec2FeatureExtractor
+
+import librosa
+import IPython.display as ipd
+import numpy as np
+import pandas as pd
+
+
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model_name_or_path = "m3hrdadfi/wav2vec2-base-100k-voxpopuli-gtzan-music"
+config = AutoConfig.from_pretrained(model_name_or_path)
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
+sampling_rate = feature_extractor.sampling_rate
+model = Wav2Vec2ForSpeechClassification.from_pretrained(model_name_or_path).to(device)
+
+
+def speech_file_to_array_fn(path, sampling_rate):
+    speech_array, _sampling_rate = torchaudio.load(path)
+    resampler = torchaudio.transforms.Resample(_sampling_rate)
+    speech = resampler(speech_array).squeeze().numpy()
+    return speech
+
+
+def predict(path, sampling_rate):
+    speech = speech_file_to_array_fn(path, sampling_rate)
+    inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
+    inputs = {key: inputs[key].to(device) for key in inputs}
+
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
+    outputs = [{"Label": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
+    return outputs
+
+
+path = "La Campanella.mp3"
+outputs = predict(path, sampling_rate)
+
+
+iface = gr.Interface(fn=predict, inputs=path, outputs=predict(path, sampling_rate))
+iface.launch()