librarian-bot's picture
Librarian Bot: Add base_model information to model
81bc87f
|
raw
history blame
1.83 kB
---
language:
- ar
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- taqwa92/tm_data
metrics:
- wer
base_model: openai/whisper-small
model-index:
- name: Whisper Small Arabic- Taqwa
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: tm_data
type: taqwa92/tm_data
config: default
split: test[:5%]
args: 'config: ar, split: test'
metrics:
- type: wer
value: 52.138728323699425
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 Small Arabic- Taqwa
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the tm_data dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5471
- Wer: 52.1387
## 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: 16
- 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: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.1628 | 5.0 | 500 | 0.5471 | 52.1387 |
### Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3