whisper-small-ru-ORD_0.7_peft_0.2 – AI Model by mizoru | AlphaNeural AI

You can deploy this model and start earning money today!

mizoru/
whisper-small-ru-ORD_0.7_peft_0.2

like

0

generated_from_trainer

openai/whisper-small

Views

No views yet

Visualize in Weights & Biases

Visualize in Weights & Biases

Visualize in Weights & Biases

Visualize in Weights & Biases

Visualize in Weights & Biases

Whisper Small Ru ORD 0.7 PEFT LoRA - Mizoru

This model is a fine-tuned version of openai/whisper-small on the ORD_0.7 dataset. It achieves the following results on the evaluation set:

Loss: 1.4241
Wer: 74.5818
Cer: 38.6379
Clean Wer: 60.9733
Clean Cer: 30.4133

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Clean Wer	Clean Cer
1.3116	1.0	196	1.2595	75.2427	37.5133	59.8253	30.3495
1.1944	2.0	392	1.2362	75.3239	38.0798	61.7830	31.1456
1.137	3.0	588	1.2391	76.7957	39.3375	62.8324	31.6562
1.0293	4.0	784	1.2472	74.9783	38.2671	58.8861	30.9703
0.9835	5.0	980	1.2720	72.7755	37.0461	58.5421	28.9427
0.92	6.0	1176	1.2871	72.1532	37.6018	62.6024	30.6224
0.849	7.0	1372	1.3214	72.6281	37.3213	58.2328	29.4501
0.7708	8.0	1568	1.3527	72.0761	37.4703	60.3471	29.9594
0.7397	9.0	1764	1.3923	74.3780	38.5124	60.8670	30.1533
0.6614	10.0	1960	1.4241	74.5818	38.6379	60.9733	30.4133

Framework versions

PEFT 0.10.1.dev0
Transformers 4.41.0.dev0
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.19.1