End of training

README.md

@@ -1,10 +1,11 @@
 ---
+library_name: transformers
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 datasets:
-- voxpopuli
+- facebook/voxpopuli
 model-index:
 - name: speecht5_finetuned_voxpopuli_it
   results: []
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_voxpopuli_it
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4707
+- Loss: 0.4783
 
 ## Model description
 
@@ -52,15 +53,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.5227        | 2.8095  | 1000 | 0.4815          |
-| 0.5148        | 5.6190  | 2000 | 0.4750          |
-| 0.5069        | 8.4284  | 3000 | 0.4722          |
-| 0.5054        | 11.2379 | 4000 | 0.4707          |
+| 0.5449        | 2.8095  | 1000 | 0.5027          |
+| 0.5237        | 5.6190  | 2000 | 0.4883          |
+| 0.5173        | 8.4284  | 3000 | 0.4799          |
+| 0.5124        | 11.2379 | 4000 | 0.4783          |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
+- Transformers 4.44.2
 - Pytorch 2.4.0+cu121
 - Datasets 2.21.0
 - Tokenizers 0.19.1

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.44.2"
 }