futureProofGlitch
commited on
Commit
•
62bf4c3
1
Parent(s):
e078745
End of training
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
-
value:
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
|
35 |
This model is a fine-tuned version of [futureProofGlitch/whisper-small](https://huggingface.co/futureProofGlitch/whisper-small) on the Gigaspeech dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Wer Ortho:
|
39 |
-
- Wer:
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -62,19 +62,15 @@ The following hyperparameters were used during training:
|
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: constant_with_warmup
|
64 |
- lr_scheduler_warmup_steps: 50
|
65 |
-
- training_steps:
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.1071 | 1.49 | 1500 | 0.3209 | 30.5425 | 18.9117 |
|
75 |
-
| 0.1174 | 1.98 | 2000 | 0.3140 | 51.1370 | 40.1655 |
|
76 |
-
| 0.0555 | 2.48 | 2500 | 0.3525 | 65.5197 | 53.9069 |
|
77 |
-
| 0.0603 | 2.98 | 3000 | 0.3434 | 56.8717 | 46.3010 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
+
value: 16.45244089773603
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
This model is a fine-tuned version of [futureProofGlitch/whisper-small](https://huggingface.co/futureProofGlitch/whisper-small) on the Gigaspeech dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.3078
|
38 |
+
- Wer Ortho: 28.4362
|
39 |
+
- Wer: 16.4524
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: constant_with_warmup
|
64 |
- lr_scheduler_warmup_steps: 50
|
65 |
+
- training_steps: 1000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
|
72 |
+
| 0.2267 | 0.5 | 500 | 0.3309 | 29.5720 | 18.0966 |
|
73 |
+
| 0.2035 | 0.99 | 1000 | 0.3078 | 28.4362 | 16.4524 |
|
|
|
|
|
|
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|