whisper-medium-21 / README.md
saif-daoud's picture
update model card README.md
be100f7
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- afrispeech-200
metrics:
- wer
model-index:
- name: whisper-medium-21
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: afrispeech-200
type: afrispeech-200
config: all
split: train
args: all
metrics:
- name: Wer
type: wer
value: 0.1798692249973202
---
<!-- 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-medium-21
This model is a fine-tuned version of [saif-daoud/whisper-medium-20](https://huggingface.co/saif-daoud/whisper-medium-20) on the afrispeech-200 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6567
- Wer: 0.1799
## 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-06
- train_batch_size: 8
- 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: 500
- training_steps: 1500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.3818 | 0.5 | 750 | 0.7995 | 0.1643 |
| 1.1218 | 1.5 | 1500 | 0.6567 | 0.1799 |
### Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2