中文Sign up

infinitejoy/wav2vec2-large-xls-r-300m-lithuanian

🤗 Hugging Face sourceautomatic-speech-recognitionapache-2.010 GBother✓ 2 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo infinitejoy/wav2vec2-large-xls-r-300m-lithuanian ./model-folder
Needs a seeder →

wav2vec2-large-xls-r-300m-lithuanian

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - LT dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1722
  • Wer: 0.2486

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: 7e-05
  • train_batch_size: 32
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2000
  • num_epochs: 50.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.6837 8.0 2000 0.6649 0.7515
1.1105 16.0 4000 0.2386 0.3436
1.0069 24.0 6000 0.2008 0.2968
0.9417 32.0 8000 0.1915 0.2774
0.887 40.0 10000 0.1819 0.2616
0.8563 48.0 12000 0.1729 0.2475

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.17.1.dev0
  • Tokenizers 0.11.0