Commit
•
972aebf
1
Parent(s):
bea0ea9
End of training
Browse files- README.md +21 -8
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -6,6 +6,8 @@ license: apache-2.0
|
|
| 6 |
base_model: openai/whisper-small
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: whisper-small-English
|
| 11 |
results: []
|
|
@@ -18,13 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
- eval_runtime: 501.1615
|
| 24 |
-
- eval_samples_per_second: 3.991
|
| 25 |
-
- eval_steps_per_second: 0.499
|
| 26 |
-
- epoch: 0.4
|
| 27 |
-
- step: 100
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -52,9 +49,25 @@ The following hyperparameters were used during training:
|
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: linear
|
| 54 |
- lr_scheduler_warmup_steps: 500
|
| 55 |
-
- training_steps:
|
| 56 |
- mixed_precision_training: Native AMP
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
### Framework versions
|
| 59 |
|
| 60 |
- Transformers 4.45.2
|
|
|
|
| 6 |
base_model: openai/whisper-small
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: whisper-small-English
|
| 13 |
results: []
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4278
|
| 24 |
+
- Accuracy: 22.4848
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 500
|
| 52 |
+
- training_steps: 1000
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 59 |
+
| 0.1469 | 0.4 | 100 | 0.3931 | 20.8666 |
|
| 60 |
+
| 0.1704 | 0.8 | 200 | 0.3690 | 20.5089 |
|
| 61 |
+
| 0.1317 | 1.2 | 300 | 0.3650 | 20.4210 |
|
| 62 |
+
| 0.1323 | 1.6 | 400 | 0.3659 | 21.3649 |
|
| 63 |
+
| 0.131 | 2.0 | 500 | 0.3675 | 21.1480 |
|
| 64 |
+
| 0.0662 | 2.4 | 600 | 0.4080 | 21.8105 |
|
| 65 |
+
| 0.0678 | 2.8 | 700 | 0.3958 | 22.5199 |
|
| 66 |
+
| 0.028 | 3.2 | 800 | 0.4290 | 22.0216 |
|
| 67 |
+
| 0.0313 | 3.6 | 900 | 0.4195 | 22.4496 |
|
| 68 |
+
| 0.032 | 4.0 | 1000 | 0.4278 | 22.4848 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
### Framework versions
|
| 72 |
|
| 73 |
- Transformers 4.45.2
|
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:aafcf40b9035062000ff50c7f4f569df2cb494bbaad4ac5cdfb0b83c37e1065f
|
| 3 |
size 966995080
|