kosamit
/

whisper-tiny-tsukuyomi

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

kosamit commited on Feb 2

Commit

88da232

•

1 Parent(s): 46b3edf

Model save

Files changed (3) hide show

README.md +9 -11
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1025
-- Wer: 15.625
 ## Model description
@@ -44,18 +44,16 @@ 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: 10
-- training_steps: 60
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 5.8578        | 3.33  | 10   | 4.9588          | 100.0  |
-| 3.1312        | 6.67  | 20   | 1.2481          | 28.125 |
-| 0.5482        | 10.0  | 30   | 0.0822          | 15.625 |
-| 0.0048        | 13.33 | 40   | 0.0833          | 15.625 |
-| 0.0002        | 16.67 | 50   | 0.0994          | 15.625 |
-| 0.0001        | 20.0  | 60   | 0.1025          | 15.625 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0655
+- Wer: 12.5
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
+- training_steps: 40
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Wer   |
+|:-------------:|:-----:|:----:|:---------------:|:-----:|
+| 5.8824        | 3.33  | 10   | 5.3742          | 100.0 |
+| 3.5587        | 6.67  | 20   | 1.4774          | 50.0  |
+| 0.7316        | 10.0  | 30   | 0.1563          | 12.5  |
+| 0.0253        | 13.33 | 40   | 0.0655          | 12.5  |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0178b4fc52ae428ddd4efeb48a39f3884667b11b372dd64c9771f57fb382b90
 size 151099494

 version https://git-lfs.github.com/spec/v1
+oid sha256:46d6b9d60492e9ebc46b7089ef7777a3cbdb08ef2f291a28f5c514c11a20409c
 size 151099494

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67dd245a9a1d28e5d4dd21e9e134a08d8d9e6a401500a17988c022e487e183b8
 size 4664

 version https://git-lfs.github.com/spec/v1
+oid sha256:9f7e1f67c196e9c558313657ae11bfc6bc90437da45c027314e4582ba2b94616
 size 4664