update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-tiny
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- PolyAI/minds14
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: whisper-tiny-en-US
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: PolyAI/minds14
|
| 18 |
+
type: PolyAI/minds14
|
| 19 |
+
config: en-US
|
| 20 |
+
split: train[450:]
|
| 21 |
+
args: en-US
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.3435655253837072
|
| 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-tiny-en-US
|
| 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: 0.6286
|
| 36 |
+
- Wer Ortho: 0.3430
|
| 37 |
+
- Wer: 0.3436
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 5e-05
|
| 57 |
+
- train_batch_size: 8
|
| 58 |
+
- eval_batch_size: 8
|
| 59 |
+
- seed: 42
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: constant_with_warmup
|
| 62 |
+
- lr_scheduler_warmup_steps: 10
|
| 63 |
+
- training_steps: 225
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
| 69 |
+
| 3.2798 | 0.25 | 14 | 0.9783 | 0.7218 | 0.6889 |
|
| 70 |
+
| 0.6283 | 0.5 | 28 | 0.5667 | 0.4479 | 0.4427 |
|
| 71 |
+
| 0.5574 | 0.75 | 42 | 0.5307 | 0.4812 | 0.4858 |
|
| 72 |
+
| 0.501 | 1.0 | 56 | 0.5130 | 0.3800 | 0.3813 |
|
| 73 |
+
| 0.2296 | 1.25 | 70 | 0.5057 | 0.3479 | 0.3436 |
|
| 74 |
+
| 0.2296 | 1.5 | 84 | 0.5515 | 0.3572 | 0.3512 |
|
| 75 |
+
| 0.2207 | 1.75 | 98 | 0.5356 | 0.3578 | 0.3530 |
|
| 76 |
+
| 0.1928 | 2.0 | 112 | 0.5288 | 0.3226 | 0.3200 |
|
| 77 |
+
| 0.0795 | 2.25 | 126 | 0.5532 | 0.3257 | 0.3259 |
|
| 78 |
+
| 0.0651 | 2.5 | 140 | 0.5833 | 0.3504 | 0.3512 |
|
| 79 |
+
| 0.0719 | 2.75 | 154 | 0.5931 | 0.3467 | 0.3501 |
|
| 80 |
+
| 0.0722 | 3.0 | 168 | 0.5994 | 0.3498 | 0.3477 |
|
| 81 |
+
| 0.0231 | 3.25 | 182 | 0.6030 | 0.3270 | 0.3264 |
|
| 82 |
+
| 0.0433 | 3.5 | 196 | 0.6059 | 0.3214 | 0.3200 |
|
| 83 |
+
| 0.0663 | 3.75 | 210 | 0.6262 | 0.3646 | 0.3648 |
|
| 84 |
+
| 0.0396 | 4.0 | 224 | 0.6286 | 0.3430 | 0.3436 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.31.0
|
| 90 |
+
- Pytorch 2.0.1+cu118
|
| 91 |
+
- Datasets 2.14.3
|
| 92 |
+
- Tokenizers 0.13.3
|