wav2vec2-assamese-asr – AI Model by bijaykumarsingh | AlphaNeural AI

You can deploy this model and start earning money today!

bijaykumarsingh/
wav2vec2-assamese-asr

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-large-xlsr-53

endpoints_compatible

Views

No views yet

wav2vec2-assamese-asr

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

Loss: 7.5922
Wer: 1.0

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
8.9934	0.4566	500	7.5918	1.0
4.341	0.9132	1000	3.6777	1.0
4.8546	1.3699	1500	3.8082	1.0
3.7788	1.8265	2000	3.5929	1.0
3.9333	2.2831	2500	3.5693	1.0
3.6451	2.7397	3000	3.5525	1.0
3.5838	3.1963	3500	3.5408	1.0
3.5768	3.6530	4000	3.5341	1.0
3.7371	4.1096	4500	3.5278	1.0
3.5569	4.5662	5000	3.5301	1.0

Framework versions

Transformers 4.46.3
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3