End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: microsoft/speecht5_tts
+base_model: fiifinketia/speecht5_finetuned_ugspeech_ak
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_ugspeech_ak
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
+This model is a fine-tuned version of [fiifinketia/speecht5_finetuned_ugspeech_ak](https://huggingface.co/fiifinketia/speecht5_finetuned_ugspeech_ak) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3869
+- Loss: 0.3787
 
 ## Model description
 
@@ -44,18 +44,33 @@ The following hyperparameters were used during training:
 - optimizer: Use 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: 100
-- training_steps: 500
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.505         | 1.0840 | 100  | 0.4380          |
-| 0.444         | 2.1680 | 200  | 0.4054          |
-| 0.4334        | 3.2520 | 300  | 0.3975          |
-| 0.4193        | 4.3360 | 400  | 0.3924          |
-| 0.4174        | 5.4201 | 500  | 0.3869          |
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 0.4157        | 0.5420  | 50   | 0.3897          |
+| 0.4205        | 1.0840  | 100  | 0.3928          |
+| 0.4263        | 1.6260  | 150  | 0.3960          |
+| 0.4187        | 2.1680  | 200  | 0.3966          |
+| 0.4247        | 2.7100  | 250  | 0.3914          |
+| 0.4161        | 3.2520  | 300  | 0.3960          |
+| 0.416         | 3.7940  | 350  | 0.3913          |
+| 0.4143        | 4.3360  | 400  | 0.3880          |
+| 0.4134        | 4.8780  | 450  | 0.3892          |
+| 0.407         | 5.4201  | 500  | 0.3871          |
+| 0.4082        | 5.9621  | 550  | 0.3829          |
+| 0.4087        | 6.5041  | 600  | 0.3865          |
+| 0.405         | 7.0461  | 650  | 0.3838          |
+| 0.4067        | 7.5881  | 700  | 0.3831          |
+| 0.3996        | 8.1301  | 750  | 0.3820          |
+| 0.4011        | 8.6721  | 800  | 0.3822          |
+| 0.3968        | 9.2141  | 850  | 0.3803          |
+| 0.4017        | 9.7561  | 900  | 0.3796          |
+| 0.3994        | 10.2981 | 950  | 0.3793          |
+| 0.3978        | 10.8401 | 1000 | 0.3787          |
 
 
 ### Framework versions