End of training
Browse files- README.md +9 -9
- generation_config.json +1 -1
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 |
|
@@ -53,7 +53,7 @@ More information needed
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
-
- learning_rate:
|
57 |
- train_batch_size: 16
|
58 |
- eval_batch_size: 16
|
59 |
- seed: 42
|
@@ -68,12 +68,12 @@ The following hyperparameters were used during training:
|
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
70 |
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
|
71 |
-
| 0.
|
72 |
|
73 |
|
74 |
### Framework versions
|
75 |
|
76 |
-
- Transformers 4.
|
77 |
-
- Pytorch 2.0
|
78 |
- Datasets 2.14.6.dev0
|
79 |
-
- Tokenizers 0.
|
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 36.36363636363637
|
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: 0.7668
|
36 |
+
- Wer Ortho: 35.9655
|
37 |
+
- Wer: 36.3636
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 3e-05
|
57 |
- train_batch_size: 16
|
58 |
- eval_batch_size: 16
|
59 |
- seed: 42
|
|
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
70 |
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
|
71 |
+
| 0.0001 | 428.57 | 500 | 0.7668 | 35.9655 | 36.3636 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
75 |
|
76 |
+
- Transformers 4.33.3
|
77 |
+
- Pytorch 2.1.0+cu118
|
78 |
- Datasets 2.14.6.dev0
|
79 |
+
- Tokenizers 0.13.3
|
generation_config.json
CHANGED
@@ -249,5 +249,5 @@
|
|
249 |
"transcribe": 50359,
|
250 |
"translate": 50358
|
251 |
},
|
252 |
-
"transformers_version": "4.
|
253 |
}
|
|
|
249 |
"transcribe": 50359,
|
250 |
"translate": 50358
|
251 |
},
|
252 |
+
"transformers_version": "4.33.3"
|
253 |
}
|