End of training

README.md

@@ -18,8 +18,6 @@ should probably proofread and complete it, then remove this comment. -->
 # JP-TTS
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the japanese-anime-speech dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
 
 ## Model description
 
@@ -47,17 +45,11 @@ The following hyperparameters were used during training:
 - 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: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.3167        | 7.09  | 1000 | nan             |
-| 3.4604        | 14.18 | 2000 | nan             |
-| 3.7115        | 21.28 | 3000 | nan             |
-| 3.4936        | 28.37 | 4000 | nan             |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebb03e7b60fca6bd3093c8c676b49e8fdcaaa1898e1cda8cbf7c0a2440d5993d
+oid sha256:ffac33a032768608632994afe2b9a8fe42acfc3df7fa3af58c96384baa3b6267
 size 577789320

runs/Feb15_15-21-49_353153eebbe4/events.out.tfevents.1708010510.353153eebbe4.263.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f737fc46559ca850408a6c6af92b32809011beea818db9d70dbc97e735e44ba
+size 6495

runs/Feb15_15-22-22_353153eebbe4/events.out.tfevents.1708010544.353153eebbe4.263.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89487e23a3c822e221e8a9aac33b36d899c0f1b3bd1db7a343ae6efe6fe0f647
+size 6532

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8dd77c895ef0335ee798c492f318f78c9eced6980d48b4c4107a67ea0f0912
+oid sha256:4ee7599ffa34660089ed4d7c8509c2911acb1c3ad7744dce3690d79496f81668
 size 5048