Instructions to use resproj007/mms_severity_classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use resproj007/mms_severity_classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="resproj007/mms_severity_classifier")# Load model directly from transformers import AutoProcessor, AutoModelForAudioClassification processor = AutoProcessor.from_pretrained("resproj007/mms_severity_classifier") model = AutoModelForAudioClassification.from_pretrained("resproj007/mms_severity_classifier") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- preprocessor_config.json +10 -0
- severity_classification_results.json +48 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
severity_classification_results.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"accuracy": 0.9786524349566378,
|
| 3 |
+
"f1_macro": 0.9776397170124734,
|
| 4 |
+
"f1_weighted": 0.9787424641046609,
|
| 5 |
+
"per_class_f1": {
|
| 6 |
+
"Mild": 0.9820971867007673,
|
| 7 |
+
"Moderate": 0.9810017271157168,
|
| 8 |
+
"Normal": 0.9634782608695652,
|
| 9 |
+
"Severe": 0.9839816933638444
|
| 10 |
+
},
|
| 11 |
+
"confusion_matrix": [
|
| 12 |
+
[
|
| 13 |
+
192,
|
| 14 |
+
0,
|
| 15 |
+
4,
|
| 16 |
+
0
|
| 17 |
+
],
|
| 18 |
+
[
|
| 19 |
+
0,
|
| 20 |
+
568,
|
| 21 |
+
11,
|
| 22 |
+
6
|
| 23 |
+
],
|
| 24 |
+
[
|
| 25 |
+
2,
|
| 26 |
+
1,
|
| 27 |
+
277,
|
| 28 |
+
0
|
| 29 |
+
],
|
| 30 |
+
[
|
| 31 |
+
1,
|
| 32 |
+
4,
|
| 33 |
+
3,
|
| 34 |
+
430
|
| 35 |
+
]
|
| 36 |
+
],
|
| 37 |
+
"label_order": [
|
| 38 |
+
"Mild",
|
| 39 |
+
"Moderate",
|
| 40 |
+
"Normal",
|
| 41 |
+
"Severe"
|
| 42 |
+
],
|
| 43 |
+
"classification_report": " precision recall f1-score support\n\n Mild 0.9846 0.9796 0.9821 196\n Moderate 0.9913 0.9709 0.9810 585\n Normal 0.9390 0.9893 0.9635 280\n Severe 0.9862 0.9817 0.9840 438\n\n accuracy 0.9787 1499\n macro avg 0.9753 0.9804 0.9776 1499\nweighted avg 0.9792 0.9787 0.9787 1499\n",
|
| 44 |
+
"model": "facebook/mms-1b-all",
|
| 45 |
+
"dataset": "resproj007/pathological_speech",
|
| 46 |
+
"train_samples": 38703,
|
| 47 |
+
"test_samples": 1499
|
| 48 |
+
}
|