End of training
Browse files- README.md +8 -8
- model.safetensors +1 -1
README.md
CHANGED
@@ -21,13 +21,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the AshtonLKY/augmented_audio dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- eval_loss: 0.
|
25 |
-
- eval_wer:
|
26 |
-
- eval_runtime:
|
27 |
-
- eval_samples_per_second: 2.
|
28 |
-
- eval_steps_per_second: 0.
|
29 |
-
- epoch:
|
30 |
-
- step:
|
31 |
|
32 |
## Model description
|
33 |
|
@@ -59,6 +59,6 @@ The following hyperparameters were used during training:
|
|
59 |
### Framework versions
|
60 |
|
61 |
- Transformers 4.44.2
|
62 |
-
- Pytorch 2.
|
63 |
- Datasets 2.21.0
|
64 |
- Tokenizers 0.19.1
|
|
|
21 |
|
22 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the AshtonLKY/augmented_audio dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- eval_loss: 0.0904
|
25 |
+
- eval_wer: 7.1378
|
26 |
+
- eval_runtime: 5253.1914
|
27 |
+
- eval_samples_per_second: 2.558
|
28 |
+
- eval_steps_per_second: 0.16
|
29 |
+
- epoch: 1.1905
|
30 |
+
- step: 4000
|
31 |
|
32 |
## Model description
|
33 |
|
|
|
59 |
### Framework versions
|
60 |
|
61 |
- Transformers 4.44.2
|
62 |
+
- Pytorch 2.4.0+cu121
|
63 |
- Datasets 2.21.0
|
64 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b2d649db227d93241be6b4806c49f982e01093db4377af908c7f1fd67f1f3df
|
3 |
size 966995080
|