You can deploy this model and start earning money today!

xuliu15/
32r_LoRA_10m

Name: 32r_LoRA_10m
Availability: InStock

peft

tensorboard

safetensors

generated_from_trainer

mozilla-foundation/common_voice_6_1

openai/whisper-small

adapter

apache-2.0

Views

No views yet

LoRA-Frisian-1h

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_6_1 dataset. It achieves the following results on the evaluation set:

Loss: 1.5372

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: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	15	3.9123
4.3581	2.0	30	2.4747
4.3581	3.0	45	2.1013
2.0139	4.0	60	1.7239
0.8458	5.0	75	1.5361
0.8458	6.0	90	1.5255
0.2525	7.0	105	1.5009
0.2525	8.0	120	1.5346
0.0726	9.0	135	1.5020
0.0233	10.0	150	1.5250
0.0233	11.0	165	1.5127
0.0152	12.0	180	1.5213
0.0152	13.0	195	1.5306
0.0104	14.0	210	1.5349
0.0093	15.0	225	1.5372

Framework versions

PEFT 0.10.0
Transformers 4.40.1
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.19.1

xuliu15/32r_LoRA_10m

LoRA-Frisian-1h

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

xuliu15/
32r_LoRA_10m