End of training

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-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0664
-- Wer: 100.4905
+- Wer: 101.2753
 
 ## Model description
 
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer      |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|
-| No log        | 6.9565  | 10   | 2.1992          | 102.3218 |
-| No log        | 13.9130 | 20   | 2.0664          | 100.4905 |
+| No log        | 6.9565  | 10   | 2.1973          | 99.4114  |
+| No log        | 13.9130 | 20   | 2.0664          | 101.2753 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99565278cd3c557ef9735e2a64e123093ed0e3d7df6fea9eca505030faad41f0
+oid sha256:d33c208ad972068bf5b998cfaaaeb8ea71b6ab40dcf8600ba7d80509abf54210
 size 3219908024

runs/Sep27_15-50-33_ip-10-0-4-196/events.out.tfevents.1727452316.ip-10-0-4-196

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b38c01eb8ade4906189749fdf881709e4ff06b80a9faaa6c6727e7730421317
-size 7416
+oid sha256:97b44eaa564b8ac6f826f5a0d8053ced6f5742ae3ac8d483b8413dbba84c0625
+size 7764