|
--- |
|
language: |
|
- sw |
|
license: apache-2.0 |
|
base_model: openai/whisper-tiny |
|
tags: |
|
- generated_from_trainer |
|
- asr |
|
- sst |
|
- swahili |
|
datasets: |
|
- mozilla-foundation/common_voice_13_0 |
|
model-index: |
|
- name: Whisper Tiny Sw - Skier8402 |
|
results: [] |
|
library_name: transformers |
|
metrics: |
|
- 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 Tiny Sw - Skier8402 |
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 13 dataset using the swahili only. |
|
|
|
## Model description |
|
|
|
More information needed. |
|
|
|
## Intended uses & limitations |
|
|
|
The model was trained without enough noise added as a form of data augmentation. Do not use this production. I recommend using a larger version of whisper with |
|
more hyperparameter tuning especially the learning rate, momentum, weight decay and adjusting the batch size. |
|
|
|
## Training and evaluation data |
|
|
|
I followed the tutorial [here](https://huggingface.co/learn/audio-course/chapter5/fine-tuning). Very minimum edits to the code were done following |
|
this tutorial. |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 500 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
