FunPang/whisper-small-Cantonese-fine-tunet-200

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2105
+- Loss: 0.2485
 - Wer: 100.0
 
 ## Model description
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer   |
 |:-------------:|:-----:|:----:|:---------------:|:-----:|
-| 0.0001        | 25.0  | 100  | 0.2022          | 112.5 |
-| 0.0001        | 50.0  | 200  | 0.2105          | 100.0 |
+| 0.0003        | 25.0  | 100  | 0.2444          | 100.0 |
+| 0.0001        | 50.0  | 200  | 0.2485          | 100.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425afd8654882ac6dbc946965315bfc926148c23e03943376bca45d0a6da45aa
+oid sha256:fd3fed4f0c98f586b1406b5dbc5b5bf691518648ecf430af06b9d5a0dcaa7e1f
 size 966995080

runs/Sep25_21-38-42_asus2/events.out.tfevents.1727325523.asus2.10312.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37722087ff9b15ef72858d2aa266655fc22457e5dc5e58deaeb23190a7224f1e
+size 8521

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbb4512a65162a1eb2b23e0798600949f0413ee290cdceba3c7f5c341f3a7fe
+oid sha256:515aeef150faee20a461376f75ee426be18e973ab79f8cfa0c119ef776c0694b
 size 5432