Model save
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
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the audiofolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Wer:
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,28 +52,22 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate: 1e-
|
56 |
- train_batch_size: 16
|
57 |
- eval_batch_size: 8
|
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: 500
|
62 |
-
- training_steps:
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
-
| Training Loss | Epoch
|
68 |
-
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.0001 | 1500.0 | 1500 | 0.0001 | 2.3166 |
|
72 |
-
| 0.0 | 2000.0 | 2000 | 0.0000 | 2.3166 |
|
73 |
-
| 0.0 | 2500.0 | 2500 | 0.0000 | 2.3166 |
|
74 |
-
| 0.0 | 3000.0 | 3000 | 0.0000 | 2.3166 |
|
75 |
-
| 0.0 | 3500.0 | 3500 | 0.0000 | 2.3166 |
|
76 |
-
| 0.0 | 4000.0 | 4000 | 0.0000 | 2.3166 |
|
77 |
|
78 |
|
79 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 80.0
|
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-small](https://huggingface.co/openai/whisper-small) on the audiofolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.9637
|
36 |
+
- Wer: 80.0
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1e-06
|
56 |
- train_batch_size: 16
|
57 |
- eval_batch_size: 8
|
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: 500
|
62 |
+
- training_steps: 1000
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----:|
|
69 |
+
| 0.7875 | 35.71 | 500 | 2.2491 | 514.0 |
|
70 |
+
| 0.0077 | 71.43 | 1000 | 1.9637 | 80.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
|
73 |
### Framework versions
|