ymoslem/whisper-small-ga2en-v5.1

Whisper Small GA-EN Speech Translation

This model is a fine-tuned version of openai/whisper-small on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset. It achieves the following results on the evaluation set:

• Loss: 1.2119
• Bleu: 30.93
• Chrf: 49.09
• Wer: 63.1247

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.02
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Bleu	Chrf	Validation Loss	Wer
2.7017	0.02	100	2.83	14.96	2.4392	169.5182
2.6732	0.04	200	7.27	22.72	1.9552	103.2868
2.1622	0.07	300	11.43	30.01	1.7297	108.2395
2.0314	0.09	400	12.96	31.0	1.6499	106.4385
1.7219	0.11	500	12.94	33.67	1.5543	107.6092
1.577	0.13	600	12.84	35.03	1.4812	118.5502
1.3569	0.1532	700	1.4559	19.94	38.08	84.2864
1.3401	0.1751	800	1.3855	13.39	36.11	126.4295
1.2272	0.1970	900	1.3764	24.39	41.75	70.7789
1.2793	0.2189	1000	1.3389	23.01	42.13	80.6844
1.0383	0.2408	1100	1.3125	23.42	43.59	82.3953
1.0485	0.2627	1200	1.2996	25.42	42.99	69.4732
1.0427	0.2846	1300	1.2996	29.24	45.36	65.6461
0.8174	0.3065	1400	1.2522	27.28	45.67	68.3926
0.7345	0.3284	1500	1.2349	26.35	46.78	79.1986
0.7551	0.3503	1600	1.2317	27.81	46.49	70.6439
0.6765	0.3722	1700	1.2062	27.62	47.46	70.9140
0.6613	0.3940	1800	1.2087	26.56	47.12	72.8050
0.6181	0.4159	1900	1.2139	29.91	48.76	65.2859
0.5809	0.4378	2000	1.2119	30.93	49.09	63.1247

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1