update model card README.md

README.md

@@ -6,20 +6,20 @@ tags:
 - text-to-speech
 - generated_from_trainer
 datasets:
-- gigaspeech
+- lj_speech
 model-index:
-- name: speecht5_tts_commonvoice_en_04_test
+- name: speecht5_tts_commonvoice_en_04
   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_tts_commonvoice_en_04_test
+# speecht5_tts_commonvoice_en_04
 
-This model is a fine-tuned version of [Avitas8485/speecht5_tts_commonvoice_en_03](https://huggingface.co/Avitas8485/speecht5_tts_commonvoice_en_03) on the gigaspeech dataset.
+This model is a fine-tuned version of [Avitas8485/speecht5_tts_commonvoice_en_03](https://huggingface.co/Avitas8485/speecht5_tts_commonvoice_en_03) on the ljspeech dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4270
+- Loss: 0.3719
 
 ## Model description
 
@@ -47,15 +47,17 @@ 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
-- training_steps: 2000
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4662        | 1.95  | 1000 | 0.4328          |
-| 0.465         | 3.9   | 2000 | 0.4270          |
+| 0.4105        | 1.36  | 1000 | 0.3789          |
+| 0.409         | 2.71  | 2000 | 0.3753          |
+| 0.4076        | 4.07  | 3000 | 0.3735          |
+| 0.4055        | 5.43  | 4000 | 0.3719          |
 
 
 ### Framework versions