End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: sophiayk20/speecht5_tts_voxpopuli_es
+base_model: sophiayk20/speecht5_tts_voxpopuli_fr
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_tts_formal_fr
 
-This model is a fine-tuned version of [sophiayk20/speecht5_tts_voxpopuli_es](https://huggingface.co/sophiayk20/speecht5_tts_voxpopuli_es) on an unknown dataset.
+This model is a fine-tuned version of [sophiayk20/speecht5_tts_voxpopuli_fr](https://huggingface.co/sophiayk20/speecht5_tts_voxpopuli_fr) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3531
+- Loss: 0.3373
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.4371        | 3.5471  | 1000 | 0.3878          |
-| 0.4023        | 7.0924  | 2000 | 0.3665          |
-| 0.395         | 10.6394 | 3000 | 0.3558          |
-| 0.3838        | 14.1847 | 4000 | 0.3531          |
+| 0.3995        | 3.5471  | 1000 | 0.3545          |
+| 0.3761        | 7.0924  | 2000 | 0.3437          |
+| 0.3742        | 10.6394 | 3000 | 0.3390          |
+| 0.3648        | 14.1847 | 4000 | 0.3373          |
 
 
 ### Framework versions

generation_config.json

@@ -5,5 +5,6 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.50.3"
+  "transformers_version": "4.50.3",
+  "use_cache": false
 }