End of training
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
-
value:
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Wer Ortho:
|
37 |
-
- Wer:
|
38 |
|
39 |
## Model description
|
40 |
|
@@ -60,21 +60,14 @@ The following hyperparameters were used during training:
|
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: constant_with_warmup
|
62 |
- lr_scheduler_warmup_steps: 50
|
63 |
-
- training_steps:
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
-
| Training Loss | Epoch
|
69 |
-
|
70 |
-
| 0.0007 | 17.86
|
71 |
-
| 0.0002 | 35.71 | 1000 | 0.9065 | 38.1242 | 36.3425 |
|
72 |
-
| 0.0001 | 53.57 | 1500 | 0.9445 | 39.6468 | 38.0897 |
|
73 |
-
| 0.0001 | 71.43 | 2000 | 0.9743 | 39.4641 | 38.0897 |
|
74 |
-
| 0.0 | 89.29 | 2500 | 1.0029 | 39.8295 | 38.4391 |
|
75 |
-
| 0.0 | 107.14 | 3000 | 1.0259 | 39.8904 | 38.5556 |
|
76 |
-
| 0.0 | 125.0 | 3500 | 1.0475 | 39.8904 | 38.6721 |
|
77 |
-
| 0.0 | 142.86 | 4000 | 1.0683 | 40.0731 | 38.8468 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 28.91705069124424
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.8974
|
36 |
+
- Wer Ortho: 30.4322
|
37 |
+
- Wer: 28.9171
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: constant_with_warmup
|
62 |
- lr_scheduler_warmup_steps: 50
|
63 |
+
- training_steps: 500
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
|
70 |
+
| 0.0007 | 17.86 | 500 | 0.8974 | 30.4322 | 28.9171 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
|
73 |
### Framework versions
|