update model card README.md

README.md

@@ -7,17 +7,7 @@ datasets:
 - facebook/voxpopuli
 model-index:
 - name: speecht5_finetuned_voxpopuli_fr
-  results:
-  - task:
-      name: Text to Speech
-      type: text-to-sppeech
-    metrics:
-    - name: MOS
-      type: mos
-      value: 0
-language:
-- fr
-pipeline_tag: text-to-speech
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5727
+- Loss: 0.5228
 
 ## Model description
 
@@ -61,10 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6151        | 34.01 | 100  | 0.6893          |
-| 0.5422        | 69.0  | 200  | 0.5647          |
-| 0.5241        | 104.0 | 300  | 0.5541          |
-| 0.5165        | 139.0 | 400  | 0.5727          |
+| 0.6882        | 2.04  | 50   | 0.6228          |
+| 0.6255        | 5.03  | 100  | 0.5841          |
+| 0.5967        | 8.02  | 150  | 0.5516          |
+| 0.5715        | 11.01 | 200  | 0.5335          |
+| 0.5614        | 14.0  | 250  | 0.5297          |
+| 0.5577        | 16.04 | 300  | 0.5236          |
+| 0.5478        | 19.03 | 350  | 0.5214          |
+| 0.5535        | 22.02 | 400  | 0.5228          |
 
 
 ### Framework versions
@@ -72,4 +66,4 @@ The following hyperparameters were used during training:
 - Transformers 4.31.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.4
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3