README.md

metadata

license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
model-index:
  - name: wav2vec2-large-mms-1b-fries-NL_common_voice_13b_other-train-validation
    results: []

wav2vec2-large-mms-1b-fries-NL_common_voice_13b_other-train-validation

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1520
• eval_wer: 0.1896
• eval_runtime: 232.3788
• eval_samples_per_second: 13.637
• eval_steps_per_second: 1.708
• epoch: 1.72
• step: 23500

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 2

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.1
• Datasets 2.14.4
• Tokenizers 0.13.3