Model save

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 metrics:
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny-hi_test
 
-This model was trained from scratch on the None dataset.
+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: 1.7256
 - Wer: 263.1579
@@ -49,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer      |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.3728        | 10.0  | 10   | 2.3405          | 101.7544 |
-| 1.5416        | 20.0  | 20   | 1.7256          | 263.1579 |
+| 2.3723        | 10.0  | 10   | 2.3402          | 101.7544 |
+| 1.5413        | 20.0  | 20   | 1.7256          | 263.1579 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6022d041323237cc30d570f083755e67ceab1edf494e74f7f17468abd81e3f6f
+oid sha256:ba5168b098450093d21677ae2522d6bc6914bdf125914c95420fcd9d0e998ab0
 size 151061672