End of training

README.md

@@ -1,6 +1,6 @@
 ---
-base_model: microsoft/speecht5_tts
 license: mit
+base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 model-index:
@@ -15,7 +15,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 0.4932
 
 ## Model description
 
@@ -43,17 +43,23 @@ 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: 4000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.9493        | 17.6991 | 1000 | nan             |
-| 0.8512        | 35.3982 | 2000 | nan             |
-| 0.8203        | 53.0973 | 3000 | nan             |
-| 0.7598        | 70.7965 | 4000 | nan             |
+| 0.8772        | 6.8966  | 100  | 0.7399          |
+| 0.8105        | 13.7931 | 200  | 0.6896          |
+| 0.6876        | 20.6897 | 300  | 0.5928          |
+| 0.5714        | 27.5862 | 400  | 0.5120          |
+| 0.5572        | 34.4828 | 500  | 0.4993          |
+| 0.539         | 41.3793 | 600  | 0.4985          |
+| 0.5276        | 48.2759 | 700  | 0.4917          |
+| 0.5219        | 55.1724 | 800  | 0.4915          |
+| 0.506         | 62.0690 | 900  | 0.4913          |
+| 0.51          | 68.9655 | 1000 | 0.4932          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73eec2dad04dc30a44a86dc1bcfc092fc979762e281999f958c60151178f403b
+oid sha256:39a9ea743dfbb9926ff5efaad5cf6ca6840fae37bd95fea2c04436b484bfd2e8
 size 577789320