whisper-large-v2 / README.md
Coletomyo's picture
optional-commit-message
3679e1d verified
---
language:
- mn
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
metrics:
- wer
base_model: openai/whisper-large-v2
model-index:
- name: Whisper Large Mongolian
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Common Voice 16.0
type: mozilla-foundation/common_voice_16_0
config: mn
split: None
args: 'config: mn, split: test'
metrics:
- type: wer
value: 37.23357981731187
name: Wer
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Large Mongolian
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the Common Voice 16.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4028
- Wer: 37.2336
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.3446 | 0.99 | 1000 | 0.4391 | 51.4572 |
| 0.1481 | 1.98 | 2000 | 0.3765 | 42.2412 |
| 0.076 | 2.97 | 3000 | 0.3830 | 39.0822 |
| 0.0149 | 3.96 | 4000 | 0.4028 | 37.2336 |
### Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2