End of training

README.md

@@ -17,7 +17,7 @@ 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 voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4609
+- Loss: 0.4434
 
 ## Model description
 
@@ -50,17 +50,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.5201        | 4.3   | 1000 | 0.4801          |
-| 0.4968        | 8.61  | 2000 | 0.4662          |
-| 0.4946        | 12.91 | 3000 | 0.4638          |
-| 0.4927        | 17.21 | 4000 | 0.4609          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4806        | 27.03  | 1000 | 0.4547          |
+| 0.4546        | 54.05  | 2000 | 0.4447          |
+| 0.4523        | 81.08  | 3000 | 0.4465          |
+| 0.45          | 108.11 | 4000 | 0.4434          |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.17.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
 - Tokenizers 0.15.2

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.38.2"
 }