End of training

README.md

@@ -7,20 +7,20 @@ base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 datasets:
-- lj_speech
+- technical
 model-index:
-- name: SpeechT5 TTS English (LJSpeech)
+- name: SpeechT5 using custom dataset
   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. -->
 
-# SpeechT5 TTS English (LJSpeech)
+# SpeechT5 using custom dataset
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the LJSpeech dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the technical_tts dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5391
+- Loss: nan
 
 ## Model description
 
@@ -53,12 +53,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss |
-|:-------------:|:-------:|:----:|:---------------:|
-| 1.5966        | 2.7137  | 1000 | 0.7347          |
-| 1.3623        | 5.4274  | 2000 | 0.6120          |
-| 1.2944        | 8.1411  | 3000 | 0.5559          |
-| 1.2932        | 10.8548 | 4000 | 0.5391          |
+| Training Loss | Epoch     | Step | Validation Loss |
+|:-------------:|:---------:|:----:|:---------------:|
+| 1.7065        | 666.6667  | 1000 | nan             |
+| 1.4393        | 1333.3333 | 2000 | nan             |
+| 1.2369        | 2000.0    | 3000 | nan             |
+| 1.1759        | 2666.6667 | 4000 | nan             |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631d9a16842035d7b54c6e89e8474f6067483306c0d5e245d3adb3c53f65c5ba
+oid sha256:7945e6247bb0de5f99223748c01d458b4ccccbdb6818235aed24d9e6e2e798c7
 size 577789320