File size: 2,845 Bytes
030e91f 9b7747e 030e91f 5e04213 030e91f 8efefae 030e91f da7437d 41e6fdd da7437d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
---
language: ru
tags:
- audio-classification
- audio
- emotion
- emotion-recognition
- emotion-classification
- speech
license: gpl-3.0
---
# Prepare and importing
```python
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchaudio
from transformers import Wav2Vec2Config, AutoModelForAudioClassification, Wav2Vec2FeatureExtractor
import librosa
import numpy as np
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
```
# Evoking:
```python
TRUST = true
config = Wav2Vec2Config.from_pretrained('Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition', trust_remote_code=TRUST)
model_ = AutoModelForAudioClassification.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition", trust_remote_code=TRUST, config=config)
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)
```
# Use case
```python
result = predict("/path/to/russian_audio_speech.wav", 16000)
print(result)
```
```python
# outputs
[{'Emotion': 'anger', 'Score': '0.0%'},
{'Emotion': 'disgust', 'Score': '100.0%'},
{'Emotion': 'enthusiasm', 'Score': '0.0%'},
{'Emotion': 'fear', 'Score': '0.0%'},
{'Emotion': 'happiness', 'Score': '0.0%'},
{'Emotion': 'neutral', 'Score': '0.0%'},
{'Emotion': 'sadness', 'Score': '0.0%'}]
```
# Results
| | precision | recall | f1-score | support |
|--------------|-----------|--------|----------|---------|
| anger | 0.97 | 0.86 | 0.92 | 44 |
| disgust | 0.71 | 0.78 | 0.74 | 37 |
| enthusiasm | 0.51 | 0.80 | 0.62 | 40 |
| fear | 0.80 | 0.62 | 0.70 | 45 |
| happiness | 0.66 | 0.70 | 0.68 | 44 |
| neutral | 0.81 | 0.66 | 0.72 | 38 |
| sadness | 0.79 | 0.59 | 0.68 | 32 |
| accuracy | | | 0.72 | 280 |
| macro avg | 0.75 | 0.72 | 0.72 | 280 |
| weighted avg | 0.75 | 0.72 | 0.73 | 280 | |