Model save

README.md

@@ -4,7 +4,7 @@ base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
 tags:
 - generated_from_trainer
 datasets:
-- narad/ravdess
+- ravdess
 metrics:
 - accuracy
 - precision
@@ -17,24 +17,24 @@ model-index:
       name: Audio Classification
       type: audio-classification
     dataset:
-      name: RAVDESS
-      type: narad/ravdess
+      name: ravdess
+      type: ravdess
       config: all
       split: train
       args: all
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7152777777777778
+      value: 0.8298611111111112
     - name: Precision
       type: precision
-      value: 0.7360657858765911
+      value: 0.8453025128787324
     - name: Recall
       type: recall
-      value: 0.7152777777777778
+      value: 0.8298611111111112
     - name: F1
       type: f1
-      value: 0.6891900402765098
+      value: 0.8329568451751053
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-large-xlsr-53-english-finetuned-ravdess
 
-This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on the RAVDESS dataset.
+This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on the ravdess dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0013
-- Accuracy: 0.7153
-- Precision: 0.7361
-- Recall: 0.7153
-- F1: 0.6892
+- Loss: 0.5624
+- Accuracy: 0.8299
+- Precision: 0.8453
+- Recall: 0.8299
+- F1: 0.8330
 
 ## Model description
 
@@ -76,16 +76,19 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 1.9323        | 1.0   | 288  | 1.9023          | 0.2917   | 0.4800    | 0.2917 | 0.2042 |
-| 1.4114        | 2.0   | 576  | 1.2845          | 0.6111   | 0.7423    | 0.6111 | 0.5283 |
-| 0.938         | 3.0   | 864  | 1.0013          | 0.7153   | 0.7361    | 0.7153 | 0.6892 |
+| 1.9765        | 1.0   | 288  | 1.9102          | 0.3090   | 0.3203    | 0.3090 | 0.1941 |
+| 1.4803        | 2.0   | 576  | 1.4590          | 0.5660   | 0.5493    | 0.5660 | 0.4811 |
+| 1.1625        | 3.0   | 864  | 1.2308          | 0.6215   | 0.6299    | 0.6215 | 0.5936 |
+| 0.8354        | 4.0   | 1152 | 0.7821          | 0.7222   | 0.7555    | 0.7222 | 0.6869 |
+| 0.2066        | 5.0   | 1440 | 0.7910          | 0.7708   | 0.8373    | 0.7708 | 0.7881 |
+| 0.6335        | 6.0   | 1728 | 0.5624          | 0.8299   | 0.8453    | 0.8299 | 0.8330 |
 
 
 ### Framework versions