End of training

README.md

@@ -4,20 +4,20 @@ base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 datasets:
-- facebook/voxpopuli
+- voxpopuli-it
 model-index:
-- name: microsoft/speecht5_tts-ft-voxpopuli-nl
+- name: speecht5_tts-ft-voxpopuli-it
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# microsoft/speecht5_tts-ft-voxpopuli-nl
+# speecht5_tts-ft-voxpopuli-it
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli-it dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4765
+- Loss: 0.5126
 
 ## Model description
 
@@ -37,27 +37,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 32
+- train_batch_size: 8
 - eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 250
+- lr_scheduler_warmup_steps: 300
 - training_steps: 1000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5251        | 8.58  | 500  | 0.4859          |
-| 0.5138        | 17.17 | 1000 | 0.4765          |
+| 0.6118        | 1.94  | 300  | 0.5508          |
+| 0.5729        | 3.89  | 600  | 0.5204          |
+| 0.563         | 5.83  | 900  | 0.5126          |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
+- Transformers 4.33.0
 - Pytorch 1.12.1+cu116
-- Datasets 2.4.0
+- Datasets 2.14.4
 - Tokenizers 0.12.1

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.0"
+}