whisper-base-ln / README.md
BrainTheos's picture
update model card README.md
a2300a7
---
language:
- ln
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Base Lingala - BrainTheos
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Fleurs
type: google/fleurs
config: ln_cd
split: validation
args: ln_cd
metrics:
- name: Wer
type: wer
value: 25.050916496945007
---
<!-- 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 Base Lingala - BrainTheos
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7265
- Wer: 25.0509
## 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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0081 | 21.0 | 1000 | 0.6218 | 29.8710 |
| 0.0016 | 42.01 | 2000 | 0.6865 | 25.1188 |
| 0.0009 | 63.01 | 3000 | 0.7152 | 24.9151 |
| 0.0007 | 85.0 | 4000 | 0.7265 | 25.0509 |
### Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.12.1.dev0
- Tokenizers 0.13.3