Model save

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 base_model: facebook/wav2vec2-base
 tags:
-- audio-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-present
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the MatsRooth/prosodic_minimal dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1590
-- Accuracy: 0.9702
+- Loss: 0.0866
+- Accuracy: 0.9853
 
 ## Model description
 
@@ -54,21 +53,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.5059        | 1.0   | 1876  | 0.2955          | 0.9328   |
-| 0.447         | 2.0   | 3753  | 0.1568          | 0.9585   |
-| 0.1397        | 3.0   | 5629  | 0.1506          | 0.9645   |
-| 0.0953        | 4.0   | 7506  | 0.1488          | 0.9672   |
-| 0.2991        | 5.0   | 9382  | 0.1518          | 0.9634   |
-| 0.2592        | 6.0   | 11259 | 0.1359          | 0.9687   |
-| 0.3824        | 7.0   | 13135 | 0.1566          | 0.9645   |
-| 0.1782        | 8.0   | 15012 | 0.1677          | 0.9668   |
-| 0.1122        | 9.0   | 16888 | 0.1657          | 0.9690   |
-| 0.1843        | 10.0  | 18760 | 0.1590          | 0.9702   |
+| 0.5208        | 1.0   | 1539  | 0.2246          | 0.9425   |
+| 0.1232        | 2.0   | 3079  | 0.1606          | 0.9655   |
+| 0.2855        | 3.0   | 4618  | 0.1177          | 0.9696   |
+| 0.2405        | 4.0   | 6158  | 0.1015          | 0.9793   |
+| 0.0272        | 5.0   | 7697  | 0.0853          | 0.9830   |
+| 0.1269        | 6.0   | 9237  | 0.1081          | 0.9807   |
+| 0.031         | 7.0   | 10776 | 0.0811          | 0.9848   |
+| 0.0781        | 8.0   | 12316 | 0.0707          | 0.9848   |
+| 0.0317        | 9.0   | 13855 | 0.0851          | 0.9848   |
+| 0.068         | 10.0  | 15390 | 0.0866          | 0.9853   |
 
 
 ### Framework versions
 
 - Transformers 4.36.0.dev0
-- Pytorch 2.1.0+cu121
+- Pytorch 2.9.0+cu128
 - Datasets 2.13.1
 - Tokenizers 0.15.0