asr-africa
/

MMS-Wolof-1-hour-Alffa-dataset

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

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

Downloads last month: 3

Safetensors

Model size

965M params

Tensor type

F32

·

Inference Providers NEW

Automatic Speech Recognition

This model is not currently available via any of the supported Inference Providers.

Model tree for asr-africa/MMS-Wolof-1-hour-Alffa-dataset

Base model

facebook/mms-1b-all

Finetuned

(258)

this model

Evaluation results

Metadata error: specify a dataset to view leaderboard