Hugging Face's logo

asr-africa
/
MMS-Wolof-1-hour-Alffa-dataset

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
MMS-Wolof-1-hour-Alffa-dataset / README.md
dmusingu's picture
dmusingu
asr-africa/MMS-Wolof-1-hour-Alffa-dataset
8e70a33 verified
preview code
|
raw
history blame contribute delete
1.83 kB
metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: MMS-Wolof-1-hour-Alffa-dataset
    results: []

Visualize in Weights & Biases

MMS-Wolof-1-hour-Alffa-dataset

This model is a fine-tuned version of facebook/mms-1b-all on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7699
  • Wer: 0.4968
  • Cer: 0.1499

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: 0.0003
  • train_batch_size: 32
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.8739 30.7692 400 0.7699 0.4968 0.1499

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0