中文Sign up

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

🤗 Hugging Face sourceautomatic-speech-recognitionapache-2.0315M params1.3 GBsafetensors✓ 3 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-latvian ./model-folder
Needs a seeder →

wav2vec2-large-xls-r-300m-latvian

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

  • Loss: 0.1892
  • Wer: 0.1698

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: 100.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.4235 12.82 2000 0.4475 0.4551
0.9383 25.64 4000 0.2235 0.2328
0.8359 38.46 6000 0.2004 0.2098
0.7633 51.28 8000 0.1960 0.1882
0.7001 64.1 10000 0.1902 0.1809
0.652 76.92 12000 0.1979 0.1775
0.6025 89.74 14000 0.1866 0.1696

Framework versions

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