Model save

README.md

@@ -3,9 +3,6 @@ library_name: transformers
 license: cc-by-nc-4.0
 base_model: csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
 tags:
-- automatic-speech-recognition
-- swagen
-- mms
 - generated_from_trainer
 model-index:
 - name: mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
@@ -17,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
 
-This model is a fine-tuned version of [csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04](https://huggingface.co/csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04) on the SWAGEN - FUS dataset.
+This model is a fine-tuned version of [csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04](https://huggingface.co/csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5986
-- Cer: 0.1646
+- Loss: 0.2920
+- Cer: 0.0722
 
 ## Model description
 
@@ -56,14 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Cer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.2434        | 0.7905 | 100  | 0.3836          | 0.0810 |
-| 0.7001        | 1.5771 | 200  | 0.3800          | 0.0898 |
-| 0.0176        | 2.3636 | 300  | 0.3785          | 0.0917 |
-| 0.2441        | 3.1502 | 400  | 0.4309          | 0.1094 |
-| 0.1854        | 3.9407 | 500  | 0.3357          | 0.0806 |
-| 0.0806        | 4.7273 | 600  | 0.3512          | 0.0871 |
-| 0.0670        | 5.5138 | 700  | 0.3521          | 0.0871 |
-| 0.3337        | 6.3004 | 800  | 0.5988          | 0.1646 |
+| 0.1146        | 0.7905 | 100  | 0.2839          | 0.0645 |
+| 0.4756        | 1.5771 | 200  | 0.2975          | 0.0715 |
+| 0.0083        | 2.3636 | 300  | 0.3000          | 0.0716 |
+| 0.2165        | 3.1502 | 400  | 0.2920          | 0.0722 |
 
 
 ### Framework versions