End of training
Browse files
README.md
CHANGED
@@ -8,22 +8,22 @@ tags:
|
|
8 |
metrics:
|
9 |
- wer
|
10 |
model-index:
|
11 |
-
- name: Whisper base fine tuned full -
|
12 |
results: []
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ashe194-700/whisper-base-fine-tuning/runs/
|
19 |
-
# Whisper base fine tuned full -
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Wer:
|
25 |
-
- Cer:
|
26 |
-
- Wer Ortho:
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -50,15 +50,16 @@ The following hyperparameters were used during training:
|
|
50 |
- total_train_batch_size: 64
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
-
- num_epochs:
|
54 |
- mixed_precision_training: Native AMP
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
-
| Training Loss | Epoch
|
59 |
-
|
60 |
-
| No log |
|
61 |
-
| No log | 2.0
|
|
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
8 |
metrics:
|
9 |
- wer
|
10 |
model-index:
|
11 |
+
- name: Whisper base fine tuned full - ashe194
|
12 |
results: []
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ashe194-700/whisper-base-fine-tuning/runs/wjyvnxax)
|
19 |
+
# Whisper base fine tuned full - ashe194
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0034
|
24 |
+
- Wer: 0.3422
|
25 |
+
- Cer: 0.3439
|
26 |
+
- Wer Ortho: 0.5124
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
50 |
- total_train_batch_size: 64
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 3
|
54 |
- mixed_precision_training: Native AMP
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Wer Ortho |
|
59 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:---------:|
|
60 |
+
| No log | 0.9935 | 76 | 0.0065 | 0.4277 | 0.2934 | 0.7385 |
|
61 |
+
| No log | 2.0 | 153 | 0.0035 | 0.3707 | 0.3717 | 0.5275 |
|
62 |
+
| No log | 2.9804 | 228 | 0.0034 | 0.3422 | 0.3439 | 0.5124 |
|
63 |
|
64 |
|
65 |
### Framework versions
|