End of training

README.md

@@ -9,18 +9,18 @@ tags:
 datasets:
 - fsicoli/twi
 model-index:
-- name: SpeechT5 TTS Twi
+- name: SpeechT5 TTS Npontu Twi
   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 Twi
+# SpeechT5 TTS Npontu Twi
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the npontu_twi dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the FsicoliTwi dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 0.3824
 
 ## Model description
 
@@ -48,17 +48,15 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.691         | 14.4928 | 1000 | nan             |
-| 0.6337        | 28.9855 | 2000 | nan             |
-| 0.6188        | 43.4783 | 3000 | nan             |
-| 0.5857        | 57.9710 | 4000 | nan             |
+| 0.4207        | 14.4928 | 1000 | 0.3869          |
+| 0.41          | 28.9855 | 2000 | 0.3824          |
 
 
 ### Framework versions