deryauysal
/

speechT5_tts_youtube_tr

speech-generation

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Community

deryauysal commited on Nov 1, 2023

Commit

7449472

•

1 Parent(s): dd78a78

End of training

Files changed (2) hide show

README.md +5 -5
pytorch_model.bin +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ 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 the test_audio_2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4447
 ## Model description
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.4558        | 76.92  | 1000 | 0.4405          |
-| 0.4098        | 153.85 | 2000 | 0.4395          |
-| 0.4128        | 230.77 | 3000 | 0.4466          |
-| 0.4185        | 307.69 | 4000 | 0.4447          |
 ### Framework versions

 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the test_audio_2 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4289
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.4584        | 76.92  | 1000 | 0.4368          |
+| 0.4099        | 153.85 | 2000 | 0.4261          |
+| 0.4123        | 230.77 | 3000 | 0.4264          |
+| 0.4182        | 307.69 | 4000 | 0.4289          |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6375471493f1053a6fa974dc2b5a14d8f19bdc5db83e638b830aec3cdb1c968
 size 577878333

 version https://git-lfs.github.com/spec/v1
+oid sha256:5871f3da75ffb07eab8adf6f902755ad3c46e545e0647976bf9f5379a90757cb
 size 577878333