Update app.py

app.py

@@ -1,15 +1,49 @@
 from transformers import pipeline
 import gradio as gr
 from pyctcdecode import BeamSearchDecoderCTC
-from Aniemore import EmotionFromVoice
 import os
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchaudio
+from transformers import AutoConfig, AutoModel, Wav2Vec2FeatureExtractor
+import librosa
+import numpy as np
 
-# emo = pipeline("audio-classification", model="Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition", trust_remote_code=True)
-emo = EmotionFromVoice()
+
+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 = [{"Emotion": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
+    return outputs
+ 
+
+TRUST = true
+
+config = AutoConfig.from_pretrained('Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition', trust_remote_code=TRUST)
+model = AutoModel.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition", trust_remote_code=TRUST)
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
 
 
 def transcribe(audio):
-    print(audio)
+    return predict(audio, 16000)
+
 
 def get_asr_interface():
     return gr.Interface(
@@ -26,7 +60,7 @@ interfaces = [
 ]
 
 names = [
-    "ASR"
+    "Russian Emotion Recognition"
 ]
 
 gr.TabbedInterface(interfaces, names).launch(server_name = "0.0.0.0", enable_queue=False)