parambharat
commited on
Commit
•
135797e
1
Parent(s):
6ccc5b7
update model card README.md
Browse files
README.md
CHANGED
@@ -1,17 +1,26 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
tags:
|
|
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
model-index:
|
5 |
-
- name:
|
6 |
results: []
|
7 |
---
|
8 |
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
should probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
-
#
|
13 |
|
14 |
-
This model
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -40,6 +49,22 @@ The following hyperparameters were used during training:
|
|
40 |
- training_steps: 5000
|
41 |
- mixed_precision_training: Native AMP
|
42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
### Framework versions
|
44 |
|
45 |
- Transformers 4.26.0.dev0
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- te
|
4 |
+
license: apache-2.0
|
5 |
tags:
|
6 |
+
- whisper-event
|
7 |
- generated_from_trainer
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
model-index:
|
11 |
+
- name: Whisper Small Te - Bharat Ramanathan
|
12 |
results: []
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
# Whisper Small Te - Bharat Ramanathan
|
19 |
|
20 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.1863
|
23 |
+
- Wer: 31.6456
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
49 |
- training_steps: 5000
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
56 |
+
| 0.1637 | 0.1 | 500 | 0.2092 | 42.9406 |
|
57 |
+
| 0.1459 | 0.2 | 1000 | 0.2025 | 35.9299 |
|
58 |
+
| 0.1348 | 0.3 | 1500 | 0.1990 | 35.4917 |
|
59 |
+
| 0.1309 | 0.4 | 2000 | 0.1974 | 33.7390 |
|
60 |
+
| 0.1253 | 0.5 | 2500 | 0.1974 | 34.0312 |
|
61 |
+
| 0.1209 | 0.6 | 3000 | 0.1909 | 32.4732 |
|
62 |
+
| 0.1139 | 1.05 | 3500 | 0.1899 | 31.7916 |
|
63 |
+
| 0.1043 | 1.15 | 4000 | 0.1868 | 31.6456 |
|
64 |
+
| 0.0996 | 1.25 | 4500 | 0.1874 | 31.6943 |
|
65 |
+
| 0.1002 | 1.35 | 5000 | 0.1863 | 31.6456 |
|
66 |
+
|
67 |
+
|
68 |
### Framework versions
|
69 |
|
70 |
- Transformers 4.26.0.dev0
|