Edit model card

wav2vec2-xls-r-300m-fleurs-mk

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m for the Macedonian language using the train and validation splits of the FLEURS dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1416
  • WER: 0.1565

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 9.3
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.1
Downloads last month
10
Safetensors
Model size
315M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for dtrifuno/wav2vec2-xls-r-300m-fleurs-mk

Finetuned
(427)
this model

Dataset used to train dtrifuno/wav2vec2-xls-r-300m-fleurs-mk