metadata

language:
  - ug
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_8_0
  - generated_from_trainer
datasets:
  - common_voice
model-index:
  - name: xls-r-uyghur-cv8
    results: []

xls-r-uyghur-cv8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UG dataset. It achieves the following results on the evaluation set:

Loss: 0.2163
Wer: 0.3249

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
3.2914	4.85	500	3.2283	1.0
3.0068	9.71	1000	2.7939	0.9980
1.4306	14.56	1500	0.4857	0.6314
1.2831	19.42	2000	0.3679	0.6066
1.2065	24.27	2500	0.3303	0.5560
1.1449	29.13	3000	0.3008	0.4690
1.0926	33.98	3500	0.2817	0.4619
1.0635	38.83	4000	0.2665	0.4391
1.029	43.69	4500	0.2616	0.4175
1.0064	48.54	5000	0.2468	0.4051
0.9659	53.4	5500	0.2394	0.3860
0.9254	58.25	6000	0.2373	0.3689
0.9209	63.11	6500	0.2347	0.3670
0.889	67.96	7000	0.2291	0.3687
0.8859	72.82	7500	0.2272	0.3616
0.8441	77.67	8000	0.2232	0.3538
0.8284	82.52	8500	0.2224	0.3382
0.8142	87.38	9000	0.2193	0.3310
0.8012	92.23	9500	0.2168	0.3276
0.7781	97.09	10000	0.2163	0.3241

Framework versions

Transformers 4.17.0.dev0
Pytorch 1.10.2+cu102
Datasets 1.18.3
Tokenizers 0.11.0