End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # TTS
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4096
 
 ## Model description
 
@@ -32,20 +34,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 2
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4133        | 6.8   | 500  | 0.4713          |
+| 0.3929        | 13.61 | 1000 | 0.4096          |
+
 
 ### Framework versions
 
-- Transformers 4.32.0
-- Pytorch 2.0.1
-- Datasets 2.14.4
+- Transformers 4.33.0.dev0
+- Pytorch 2.0.1+cu118
 - Tokenizers 0.13.3

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.32.0"
+  "transformers_version": "4.33.0.dev0"
 }