Ar4ikov commited on
Commit
8efefae
1 Parent(s): 213d368

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -0
README.md CHANGED
@@ -10,6 +10,70 @@ tags:
10
  license: gpl-3.0
11
  ---
12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  # Results
14
 
15
  | | precision | recall | f1-score | support |
10
  license: gpl-3.0
11
  ---
12
 
13
+ # Prepare and importing
14
+
15
+ ```python
16
+ import torch
17
+ import torch.nn as nn
18
+ import torch.nn.functional as F
19
+ import torchaudio
20
+ from transformers import Wav2Vec2Config, AutoModelForAudioClassification, Wav2Vec2FeatureExtractor
21
+
22
+ import librosa
23
+ import numpy as np
24
+
25
+
26
+ def speech_file_to_array_fn(path, sampling_rate):
27
+ speech_array, _sampling_rate = torchaudio.load(path)
28
+ resampler = torchaudio.transforms.Resample(_sampling_rate)
29
+ speech = resampler(speech_array).squeeze().numpy()
30
+ return speech
31
+
32
+
33
+ def predict(path, sampling_rate):
34
+ speech = speech_file_to_array_fn(path, sampling_rate)
35
+ inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
36
+ inputs = {key: inputs[key].to(device) for key in inputs}
37
+
38
+ with torch.no_grad():
39
+ logits = model_(**inputs).logits
40
+
41
+ scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
42
+ outputs = [{"Emotion": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
43
+ return outputs
44
+ ```
45
+
46
+ # Evoking:
47
+
48
+ ```python
49
+ TRUST = true
50
+
51
+ config = Wav2Vec2Config.from_pretrained('Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition', trust_remote_code=TRUST)
52
+ model_ = AutoModelForAudioClassification.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition", trust_remote_code=TRUST, config=config)
53
+ feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition")
54
+
55
+ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
56
+ model_.to(device)
57
+ ```
58
+
59
+ # Use case
60
+
61
+ ```python
62
+ result = predict("/path/to/russian_audio_speech.wav", 16000)
63
+ print(result)
64
+ ```
65
+
66
+ ```python
67
+ # outputs
68
+ [{'Emotion': 'anger', 'Score': '0.0%'},
69
+ {'Emotion': 'disgust', 'Score': '100.0%'},
70
+ {'Emotion': 'enthusiasm', 'Score': '0.0%'},
71
+ {'Emotion': 'fear', 'Score': '0.0%'},
72
+ {'Emotion': 'happiness', 'Score': '0.0%'},
73
+ {'Emotion': 'neutral', 'Score': '0.0%'},
74
+ {'Emotion': 'sadness', 'Score': '0.0%'}]
75
+ ```
76
+
77
  # Results
78
 
79
  | | precision | recall | f1-score | support |