update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- google/fleurs
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: whisper-small-bn-in
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: google/fleurs
|
| 18 |
+
type: google/fleurs
|
| 19 |
+
config: bn_in
|
| 20 |
+
split: train+validation
|
| 21 |
+
args: bn_in
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.45676500508647
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# whisper-small-bn-in
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.1842
|
| 36 |
+
- Wer: 0.4568
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 1e-05
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 16
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: constant_with_warmup
|
| 61 |
+
- lr_scheduler_warmup_steps: 5
|
| 62 |
+
- training_steps: 2000
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 68 |
+
| 0.4443 | 0.53 | 100 | 0.3399 | 0.7272 |
|
| 69 |
+
| 0.249 | 1.07 | 200 | 0.2222 | 0.6244 |
|
| 70 |
+
| 0.1662 | 1.6 | 300 | 0.1778 | 0.5807 |
|
| 71 |
+
| 0.1221 | 2.14 | 400 | 0.1602 | 0.5397 |
|
| 72 |
+
| 0.0965 | 2.67 | 500 | 0.1484 | 0.5168 |
|
| 73 |
+
| 0.0646 | 3.21 | 600 | 0.1475 | 0.4966 |
|
| 74 |
+
| 0.0566 | 3.74 | 700 | 0.1420 | 0.4812 |
|
| 75 |
+
| 0.028 | 4.28 | 800 | 0.1511 | 0.4910 |
|
| 76 |
+
| 0.0325 | 4.81 | 900 | 0.1476 | 0.4766 |
|
| 77 |
+
| 0.0177 | 5.35 | 1000 | 0.1593 | 0.4876 |
|
| 78 |
+
| 0.0176 | 5.88 | 1100 | 0.1589 | 0.4715 |
|
| 79 |
+
| 0.0127 | 6.42 | 1200 | 0.1622 | 0.4634 |
|
| 80 |
+
| 0.0126 | 6.95 | 1300 | 0.1706 | 0.4673 |
|
| 81 |
+
| 0.0089 | 7.49 | 1400 | 0.1777 | 0.4712 |
|
| 82 |
+
| 0.0087 | 8.02 | 1500 | 0.1776 | 0.4666 |
|
| 83 |
+
| 0.0076 | 8.56 | 1600 | 0.1788 | 0.4505 |
|
| 84 |
+
| 0.007 | 9.09 | 1700 | 0.1906 | 0.4685 |
|
| 85 |
+
| 0.0057 | 9.63 | 1800 | 0.1840 | 0.4573 |
|
| 86 |
+
| 0.0064 | 10.16 | 1900 | 0.1841 | 0.4569 |
|
| 87 |
+
| 0.0057 | 10.7 | 2000 | 0.1842 | 0.4568 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.32.0.dev0
|
| 93 |
+
- Pytorch 1.12.1+cu116
|
| 94 |
+
- Datasets 2.4.0
|
| 95 |
+
- Tokenizers 0.12.1
|