Commit
•
a324cfb
1
Parent(s):
ab2d361
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,18 +1,26 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
-
- name:
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
-
#
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [openai/whisper-
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -41,6 +49,22 @@ The following hyperparameters were used during training:
|
|
| 41 |
- training_steps: 5000
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- 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 Base 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 Base 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: 0.2455
|
| 23 |
+
- Wer: 42.6485
|
| 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 |
+
| 0.6341 | 0.1 | 500 | 0.3894 | 60.7108 |
|
| 57 |
+
| 0.349 | 0.2 | 1000 | 0.3081 | 52.0935 |
|
| 58 |
+
| 0.2792 | 0.3 | 1500 | 0.2874 | 49.7079 |
|
| 59 |
+
| 0.2433 | 0.4 | 2000 | 0.2720 | 47.5657 |
|
| 60 |
+
| 0.2224 | 1.06 | 2500 | 0.2632 | 45.2288 |
|
| 61 |
+
| 0.2058 | 1.16 | 3000 | 0.2529 | 44.3038 |
|
| 62 |
+
| 0.1944 | 1.26 | 3500 | 0.2519 | 44.5959 |
|
| 63 |
+
| 0.1869 | 1.36 | 4000 | 0.2475 | 43.7196 |
|
| 64 |
+
| 0.1811 | 2.03 | 4500 | 0.2451 | 43.3301 |
|
| 65 |
+
| 0.1775 | 2.13 | 5000 | 0.2455 | 42.6485 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- Transformers 4.26.0.dev0
|