metadata

base_model: facebook/mms-1b-all
datasets:
  - common_voice_17_0
library_name: transformers
license: cc-by-nc-4.0
tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-mms-1b-CV17.0
    results: []

wav2vec2-mms-1b-CV17.0

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

eval_loss: 0.2564
eval_wer: 0.4162
eval_cer: 0.0698
eval_bleu: 0.3568
eval_runtime: 202.4945
eval_samples_per_second: 11.921
eval_steps_per_second: 1.491
epoch: 4.2105
step: 1200

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: 0.001
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.15
training_steps: 2000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 3.0.0
Tokenizers 0.19.1