update model card README.md

README.md

@@ -1,18 +1,24 @@
 ---
+language:
+- en
 license: mit
 tags:
 - generated_from_trainer
+datasets:
+- speecht5_finetuned_single_speaker_en_test_librivox
 model-index:
-- name: speecht5_finetuned_single_speaker_en_test_librivox
+- name: SpeechT5 Single Speaker test
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# speecht5_finetuned_single_speaker_en_test_librivox
+# SpeechT5 Single Speaker test
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the single_speaker_en_test_librivox dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3865
 
 ## Model description
 
@@ -40,10 +46,16 @@ 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_steps: 500
-- num_epochs: 3.0
+- training_steps: 4000
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4198        | 12.44 | 1000 | 0.3884          |
+| 0.4006        | 24.88 | 2000 | 0.3901          |
+| 0.3883        | 37.33 | 3000 | 0.3875          |
+| 0.3878        | 49.77 | 4000 | 0.3865          |
 
 
 ### Framework versions