You can deploy this model and start earning money today!

mfaiq2307/
faiq-wav2vec2-large-xlsr-indo-demo-v100

Name: faiq-wav2vec2-large-xlsr-indo-demo-v100
Availability: InStock

automatic-speech-recognition

generated_from_trainer

Views

No views yet

faiq-wav2vec2-large-xlsr-indo-demo-v100

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3986
Wer: 0.4268

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: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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: 500
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.0166	2.92	400	2.8107	1.0
1.2378	5.84	800	0.4595	0.6213
0.3819	8.76	1200	0.4255	0.5515
0.2653	11.68	1600	0.4023	0.4949
0.2146	14.6	2000	0.3780	0.4760
0.1711	17.52	2400	0.4098	0.4609
0.1537	20.44	2800	0.4049	0.4495
0.1316	23.36	3200	0.3978	0.4408
0.1202	26.28	3600	0.3929	0.4282
0.1095	29.2	4000	0.3986	0.4268

Framework versions

Transformers 4.28.0
Pytorch 2.0.0+cu118
Datasets 2.6.1
Tokenizers 0.13.3

mfaiq2307/faiq-wav2vec2-large-xlsr-indo-demo-v100

faiq-wav2vec2-large-xlsr-indo-demo-v100

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mfaiq2307/
faiq-wav2vec2-large-xlsr-indo-demo-v100