KELONMYOSA
commited on
Commit
•
383d0b8
1
Parent(s):
ccd8444
Update README.md
Browse files
README.md
CHANGED
@@ -30,6 +30,22 @@ The dataset used to fine-tune the original pre-trained model is the [DUSHA datas
|
|
30 |
emotions = ['neutral', 'positive', 'angry', 'sad', 'other']
|
31 |
```
|
32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
It achieves the following results:
|
34 |
- Training Loss: 0.528700
|
35 |
- Validation Loss: 0.349617
|
|
|
30 |
emotions = ['neutral', 'positive', 'angry', 'sad', 'other']
|
31 |
```
|
32 |
|
33 |
+
# How to use
|
34 |
+
|
35 |
+
```python
|
36 |
+
from transformers.pipelines import pipeline
|
37 |
+
|
38 |
+
pipe = pipeline(model="KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru", trust_remote_code=True)
|
39 |
+
|
40 |
+
result = pipe("speech.wav")
|
41 |
+
print(result)
|
42 |
+
```
|
43 |
+
~~~
|
44 |
+
[{'label': 'neutral', 'score': 0.00318}, {'label': 'positive', 'score': 0.00376}, {'label': 'sad', 'score': 0.00145}, {'label': 'angry', 'score': 0.98984}, {'label': 'other', 'score': 0.00176}]
|
45 |
+
~~~
|
46 |
+
|
47 |
+
# Evaluation
|
48 |
+
|
49 |
It achieves the following results:
|
50 |
- Training Loss: 0.528700
|
51 |
- Validation Loss: 0.349617
|