You can deploy this model and start earning money today!

nik1509/
xlsr300m_telugu_finetuned_optimizer_ablation_adam

Name: xlsr300m_telugu_finetuned_optimizer_ablation_adam
Availability: InStock

transformers

safetensors

wav2vec2

automatic-speech-recognition

generated_from_trainer

nik1509/telugu_wav2vecmedium_basemodel

finetune

apache-2.0

endpoints_compatible

Views

No views yet

xlsr300m_telugu_finetuned_optimizer_ablation_adam

This model is a fine-tuned version of nik1509/telugu_wav2vecmedium_basemodel on the None dataset. It achieves the following results on the evaluation set:

Loss: 567.5811
Wer: 0.3937
Cer: 0.1661

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
278.418	1.0	1152	457.7748	0.3984	0.1654
277.7894	2.0	2304	458.8120	0.4010	0.1661
303.1747	3.0	3456	458.5554	0.4016	0.1664
297.2808	4.0	4608	458.5729	0.4037	0.1671
297.4547	5.0	5760	479.2428	0.4019	0.1665
314.4776	6.0	6912	478.6219	0.3977	0.1652
285.9929	7.0	8064	486.5857	0.4000	0.1660
284.8561	8.0	9216	488.8567	0.4013	0.1674
280.5861	9.0	10368	508.6522	0.3998	0.1664
266.5997	10.0	11520	507.9496	0.4026	0.1679
251.7131	11.0	12672	518.1205	0.3987	0.1670
295.7108	12.0	13824	528.9866	0.3949	0.1665
239.2476	13.0	14976	534.6765	0.3962	0.1665
263.5965	14.0	16128	541.5568	0.3951	0.1664
265.3468	15.0	17280	567.5811	0.3937	0.1661

Framework versions

Transformers 4.53.1
Pytorch 2.8.0.dev20250609+cu118
Datasets 3.6.0
Tokenizers 0.21.2

nik1509/xlsr300m_telugu_finetuned_optimizer_ablation_adam

xlsr300m_telugu_finetuned_optimizer_ablation_adam

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

nik1509/
xlsr300m_telugu_finetuned_optimizer_ablation_adam