update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- pt
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- hf-asr-leaderboard
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- mozilla-foundation/common_voice_11_0
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
+
model-index:
|
| 13 |
+
- name: Whisper Tiny PT with Common Voice 11
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Common Voice 11.0
|
| 20 |
+
type: mozilla-foundation/common_voice_11_0
|
| 21 |
+
args: 'config: pt, split: test'
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 33.24473522796974
|
| 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 PT with Common Voice 11
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5205
|
| 36 |
+
- Wer: 33.2447
|
| 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: 8
|
| 57 |
+
- eval_batch_size: 1
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- training_steps: 16000
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
| 67 |
+
| 0.3154 | 0.44 | 1000 | 0.4987 | 36.2196 |
|
| 68 |
+
| 0.3252 | 0.88 | 2000 | 0.4586 | 33.6213 |
|
| 69 |
+
| 0.1989 | 1.32 | 3000 | 0.4457 | 32.7455 |
|
| 70 |
+
| 0.3112 | 1.76 | 4000 | 0.4356 | 31.4097 |
|
| 71 |
+
| 0.1329 | 2.2 | 5000 | 0.4348 | 31.1559 |
|
| 72 |
+
| 0.1193 | 2.64 | 6000 | 0.4343 | 31.4046 |
|
| 73 |
+
| 0.0723 | 3.07 | 7000 | 0.4424 | 31.5869 |
|
| 74 |
+
| 0.0698 | 3.51 | 8000 | 0.4497 | 32.0827 |
|
| 75 |
+
| 0.0865 | 3.95 | 9000 | 0.4497 | 31.0945 |
|
| 76 |
+
| 0.0522 | 4.39 | 10000 | 0.4716 | 32.2190 |
|
| 77 |
+
| 0.0542 | 4.83 | 11000 | 0.4761 | 32.6944 |
|
| 78 |
+
| 0.061 | 5.27 | 12000 | 0.4983 | 32.0691 |
|
| 79 |
+
| 0.0459 | 5.71 | 13000 | 0.4985 | 32.4968 |
|
| 80 |
+
| 0.0338 | 6.15 | 14000 | 0.5123 | 33.3129 |
|
| 81 |
+
| 0.0492 | 6.59 | 15000 | 0.5217 | 33.2686 |
|
| 82 |
+
| 0.0194 | 7.03 | 16000 | 0.5205 | 33.2447 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.25.0.dev0
|
| 88 |
+
- Pytorch 1.13.0+cu117
|
| 89 |
+
- Datasets 2.6.1
|
| 90 |
+
- Tokenizers 0.13.1
|