End of training

README.md

@@ -4,8 +4,6 @@ license: mit
 base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
-datasets:
-- audiofolder
 model-index:
 - name: demo_text_to_speech
   results: []
@@ -16,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # demo_text_to_speech
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the audiofolder dataset.
+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: 0.4674
+- Loss: 0.4399
 
 ## Model description
 
@@ -45,25 +43,24 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 1200
+- lr_scheduler_warmup_steps: 200
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch    | Step | Validation Loss |
-|:-------------:|:--------:|:----:|:---------------:|
-| 0.6847        | 39.8696  | 200  | 0.5010          |
-| 0.5393        | 79.8696  | 400  | 0.4659          |
-| 0.4964        | 119.8696 | 600  | 0.4596          |
-| 0.4861        | 159.8696 | 800  | 0.4680          |
-| 0.4786        | 199.8696 | 1000 | 0.4675          |
-| 0.4741        | 239.8696 | 1200 | 0.4674          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5642        | 16.64 | 200  | 0.5134          |
+| 0.4948        | 33.32 | 400  | 0.4464          |
+| 0.4797        | 49.96 | 600  | 0.4396          |
+| 0.4792        | 66.64 | 800  | 0.4400          |
+| 0.4728        | 83.32 | 1000 | 0.4399          |
 
 
 ### Framework versions
 
-- Transformers 4.50.3
-- Pytorch 2.6.0+cu124
+- Transformers 4.51.1
+- Pytorch 2.5.1+cu124
 - Datasets 3.5.0
-- Tokenizers 0.21.1
+- Tokenizers 0.21.0

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.50.3"
+  "transformers_version": "4.51.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac80fb485a1d913f0383c14184ee87e43c1eaf8b2dfab6cffad19dae118cf5aa
+oid sha256:efc921262abb49f5a2dd8db0bf691df9ebc20a38852d90f0d7ff8f9624727a01
 size 577789320