End of training

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.3725
+- Loss: 0.3868
 
 ## Model description
 
@@ -42,24 +43,22 @@ The following hyperparameters were used during training:
 - 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: 500
-- training_steps: 500
+- lr_scheduler_warmup_steps: 5000
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6237        | 0.2540 | 100  | 0.5085          |
-| 0.5744        | 0.5079 | 200  | 0.4722          |
-| 0.4577        | 0.7619 | 300  | 0.3953          |
-| 0.4272        | 1.0159 | 400  | 0.3801          |
-| 0.4155        | 1.2698 | 500  | 0.3725          |
+| 0.6522        | 0.9989 | 354  | 0.5330          |
+| 0.5573        | 1.9979 | 708  | 0.4585          |
+| 0.4417        | 2.9968 | 1062 | 0.3868          |
 
 
 ### Framework versions
 
-- Transformers 4.42.3
-- Pytorch 2.1.2
-- Datasets 2.20.0
+- Transformers 4.44.2
+- Pytorch 2.4.0
+- Datasets 3.0.0
 - Tokenizers 0.19.1

config.json

@@ -85,7 +85,7 @@
   "speech_decoder_prenet_layers": 2,
   "speech_decoder_prenet_units": 256,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.44.2",
   "use_cache": false,
   "use_guided_attention_loss": true,
   "vocab_size": 81

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f44f1dab7a1837fdd2b3889ccac8010ba40cba30856ff4f5dab962885bff8f7
+oid sha256:d79601d2d95edc044d365df1b5ebdd6985cec0432295a052489d0570900d6c95
 size 577789320

runs/Oct15_17-08-29_d1eba1fcf911/events.out.tfevents.1729012112.d1eba1fcf911.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01aa172702387518c58a414d1c22e51f87a1c379f62d6667a8bc92a4efab20e6
+size 16555

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7646afceb4953a76cfc29c81ca8283d930725cd1c7f75f8c566051d3318b5701
-size 5304
+oid sha256:a87420c29df410df1e1cf8fcb12fbeb9006a38d0494b77319350525f494661a1
+size 5368