Hugging Face's logo

imvladikon
/
wav2vec2-xls-r-300m-hebrew

Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Hebrew
wav2vec2
Generated from Trainer
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Community
2
wav2vec2-xls-r-300m-hebrew / README.md
imvladikon's picture
imvladikon
init
f6079f4
preview code
|
raw
history blame
3.6 kB
metadata
language:
  - he
tags:
  - automatic-speech-recognition
  - robust-speech-event
  - he
  - generated_from_trainer
model-index:
  - name: wav2vec2-xls-r-300m-hebrew
    results: []

wav2vec2-xls-r-300m-hebrew

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the private dataset with stats:

split size n_samples duration(hrs)
train 4.19gb 20306 28
dev 1.05gb 5076 7

It achieves the following results on the evaluation set:

  • Loss: 0.5438
  • Wer: 0.1773

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
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 100.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 3.15 1000 0.5203 0.4333
1.4284 6.31 2000 0.4816 0.3951
1.4284 9.46 3000 0.4315 0.3546
1.283 12.62 4000 0.4278 0.3404
1.283 15.77 5000 0.4090 0.3054
1.1777 18.93 6000 0.3893 0.3006
1.1777 22.08 7000 0.3968 0.2857
1.0994 25.24 8000 0.3892 0.2751
1.0994 28.39 9000 0.4061 0.2690
1.0323 31.54 10000 0.4114 0.2507
1.0323 34.7 11000 0.4021 0.2508
0.9623 37.85 12000 0.4032 0.2378
0.9623 41.01 13000 0.4148 0.2374
0.9077 44.16 14000 0.4350 0.2323
0.9077 47.32 15000 0.4515 0.2246
0.8573 50.47 16000 0.4474 0.2180
0.8573 53.63 17000 0.4649 0.2171
0.8083 56.78 18000 0.4455 0.2102
0.8083 59.94 19000 0.4587 0.2092
0.769 63.09 20000 0.4794 0.2012
0.769 66.25 21000 0.4845 0.2007
0.7308 69.4 22000 0.4937 0.2008
0.7308 72.55 23000 0.4920 0.1895
0.6927 75.71 24000 0.5179 0.1911
0.6927 78.86 25000 0.5202 0.1877
0.6622 82.02 26000 0.5266 0.1840
0.6622 85.17 27000 0.5351 0.1854
0.6315 88.33 28000 0.5373 0.1811
0.6315 91.48 29000 0.5331 0.1792
0.6075 94.64 30000 0.5390 0.1779
0.6075 97.79 31000 0.5459 0.1773

Framework versions

  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 1.18.2.dev0
  • Tokenizers 0.11.0