End of training

README.md

@@ -21,7 +21,7 @@ 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 common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4717
+- Loss: 0.4646
 
 ## Model description
 
@@ -56,12 +56,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6621        | 0.4522 | 100  | 0.5657          |
-| 0.6034        | 0.9045 | 200  | 0.5272          |
-| 0.5675        | 1.3567 | 300  | 0.5172          |
-| 0.5411        | 1.8089 | 400  | 0.4878          |
-| 0.5266        | 2.2612 | 500  | 0.4778          |
-| 0.5176        | 2.7134 | 600  | 0.4717          |
+| 5.3349        | 0.3442 | 100  | 0.5973          |
+| 4.7257        | 0.6885 | 200  | 0.5412          |
+| 4.3821        | 1.0327 | 300  | 0.5127          |
+| 4.283         | 1.3769 | 400  | 0.4926          |
+| 4.1735        | 1.7212 | 500  | 0.4865          |
+| 4.0968        | 2.0654 | 600  | 0.4790          |
+| 4.0861        | 2.4096 | 700  | 0.4687          |
+| 3.9972        | 2.7539 | 800  | 0.4646          |
 
 
 ### Framework versions

runs/Oct18_03-41-12_8229a52d777c/events.out.tfevents.1729222876.8229a52d777c.1259.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6a9a66fb83d2bea800e002e9e90f687ae3ebb3c46bc64d191340cd3306260a
-size 15543
+oid sha256:8949e0b5764b226f38f613c1a280eaa43d2de7b87d944a9534140a3b34cbd1a9
+size 16319