Aaquila/tts_speecht5_accentdb

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # fine_tuned
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4328
 
 ## Model description
 
@@ -44,6 +46,22 @@ The following hyperparameters were used during training:
 - training_steps: 2500
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5769        | 8.77  | 250  | 0.5205          |
+| 0.4998        | 17.54 | 500  | 0.4383          |
+| 0.4637        | 26.32 | 750  | 0.4285          |
+| 0.4488        | 35.09 | 1000 | 0.4298          |
+| 0.4307        | 43.86 | 1250 | 0.4272          |
+| 0.4309        | 52.63 | 1500 | 0.4245          |
+| 0.4272        | 61.4  | 1750 | 0.4282          |
+| 0.4204        | 70.18 | 2000 | 0.4317          |
+| 0.4222        | 78.95 | 2250 | 0.4313          |
+| 0.4354        | 87.72 | 2500 | 0.4328          |
+
+
 ### Framework versions
 
 - Transformers 4.38.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc53a58192c13cef149410f0469e13fcbd57f2548cd51e5f4c34c5bc3cd20f32
+oid sha256:013172ed5367073d88d4766aa65dc7877d0bcbaf62e20a5fb6c87dafa90e6562
 size 577789320