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
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the model_eng dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Wer:
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -57,18 +57,23 @@ The following hyperparameters were used during training:
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
-
- num_epochs:
|
61 |
- mixed_precision_training: Native AMP
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
67 |
-
| No log | 1.0 | 15 |
|
68 |
-
| No log | 2.0 | 30 | 0.
|
69 |
-
| No log | 3.0 | 45 | 0.
|
70 |
-
| No log | 4.0 | 60 | 0.
|
71 |
-
| No log | 5.0 | 75 | 0.
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 9.442870632672333
|
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.en](https://huggingface.co/openai/whisper-tiny.en) on the model_eng dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.0162
|
35 |
+
- Wer: 9.4429
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 10
|
61 |
- mixed_precision_training: Native AMP
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
67 |
+
| No log | 1.0 | 15 | 0.2506 | 15.9585 |
|
68 |
+
| No log | 2.0 | 30 | 0.1447 | 13.9754 |
|
69 |
+
| No log | 3.0 | 45 | 0.0945 | 11.4259 |
|
70 |
+
| No log | 4.0 | 60 | 0.0657 | 11.7092 |
|
71 |
+
| No log | 5.0 | 75 | 0.0480 | 11.4259 |
|
72 |
+
| No log | 6.0 | 90 | 0.0322 | 9.9150 |
|
73 |
+
| No log | 7.0 | 105 | 0.0243 | 10.1983 |
|
74 |
+
| No log | 8.0 | 120 | 0.0196 | 9.2540 |
|
75 |
+
| No log | 9.0 | 135 | 0.0171 | 9.4429 |
|
76 |
+
| No log | 10.0 | 150 | 0.0162 | 9.4429 |
|
77 |
|
78 |
|
79 |
### Framework versions
|