mikr/whisper-large2-czech-cv11-v2

Whisper Large-v2 Czech CV11 v2

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 cs dataset. It achieves the following results on the evaluation set:

• Loss: 0.2120
• Wer: 9.0459

Model description

Fine tuned with deepspeed optimization and batch_size: 32.

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: 32
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0106	4.24	1000	0.1625	9.9888
0.0034	8.47	2000	0.1841	9.8304
0.0011	12.71	3000	0.1917	9.4031
0.0004	16.95	4000	0.2075	9.1177
0.0003	21.19	5000	0.2120	9.0459

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2