metadata
language:
- ga-IE
license: apache-2.0
tags:
- automatic-speech-recognition
- mozilla-foundation/common_voice_8_0
- generated_from_trainer
- ga-IE
- robust-speech-event
- hf-asr-leaderboard
datasets:
- mozilla-foundation/common_voice_8_0
model-index:
- name: wav2vec-1b-cv8-ir
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 8
type: mozilla-foundation/common_voice_8_0
args: ga-IE
metrics:
- name: Test WER
type: wer
value: 43.7
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - GA-IE dataset. It achieves the following results on the evaluation set:
- Loss: 0.8445
- Wer: 0.5585
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 60.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.7135 | 31.24 | 500 | 0.9609 | 0.6926 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0