Commit
•
8f29dd4
1
Parent(s):
a52aa74
update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value:
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Wer Ortho:
|
36 |
-
- Wer:
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -58,24 +58,23 @@ The following hyperparameters were used during training:
|
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
-
- lr_scheduler_warmup_steps: 150
|
62 |
- training_steps: 500
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer
|
68 |
-
|
69 |
-
|
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
|
80 |
|
81 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 0.3541912632821724
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.6875
|
35 |
+
- Wer Ortho: 0.3745
|
36 |
+
- Wer: 0.3542
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
|
|
61 |
- training_steps: 500
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
68 |
+
| 0.6838 | 1.79 | 50 | 0.6522 | 0.4028 | 0.3613 |
|
69 |
+
| 0.2778 | 3.57 | 100 | 0.5727 | 0.3880 | 0.3589 |
|
70 |
+
| 0.1313 | 5.36 | 150 | 0.5870 | 0.3794 | 0.3501 |
|
71 |
+
| 0.0539 | 7.14 | 200 | 0.6080 | 0.3726 | 0.3471 |
|
72 |
+
| 0.022 | 8.93 | 250 | 0.6380 | 0.3745 | 0.3477 |
|
73 |
+
| 0.0095 | 10.71 | 300 | 0.6629 | 0.3843 | 0.3595 |
|
74 |
+
| 0.0049 | 12.5 | 350 | 0.6715 | 0.3819 | 0.3583 |
|
75 |
+
| 0.0036 | 14.29 | 400 | 0.6811 | 0.3825 | 0.3595 |
|
76 |
+
| 0.0032 | 16.07 | 450 | 0.6858 | 0.3757 | 0.3554 |
|
77 |
+
| 0.0029 | 17.86 | 500 | 0.6875 | 0.3745 | 0.3542 |
|
78 |
|
79 |
|
80 |
### Framework versions
|