whisper-large-v2-translate-zh-v0.2-st

fadffaffdf/whisper-large-v2-translate-zh-v0.2-st

whisper-large-v2-translate-zh-v0.2-st is a automatic speech recognition model from fadffaffdf. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

This model is a fine-tuned version of openai/whisper-large-v2. It achieves the following results on the evaluation set: - Loss: 1.2328 - Ter: 60.4828 - Bleu: 29.3658 - Cer: 0.6602

Downloads · 30 days

5% of all-time downloads

All-time downloads

Public

Parameters

1.6B

3.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors3.2 GB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Apr 27, 2026
Updated: Apr 27, 2026
SHA: d35e5a98

Base models

openai/whisper-large-v2

Model card

From the Hugging Face model README

whisper-large-v2-translate-zh-v0.2-st

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

Loss: 1.2328
Ter: 60.4828
Bleu: 29.3658
Cer: 0.6602

Model	TER	BLEU	CER
v2-zh-v0.2-st	60.4828	29.3658	0.6602
v2-zh-v0.1-lt	65.0566	30.0034	0.7102
v3-zh-v0.1-lt	67.1971	27.6572	0.7328

Model description

5000小时 (日语音频,中文带轴字幕) 数据微调, 翻译模式直出中文

Usage

task='translate', language='ja'

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: 1.5e-05
seed: 1145141919
total_train_batch_size: 256
optimizer: adamw with betas=(0.9,0.98) and epsilon=1e-06
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7.0

Training results

Training Loss	Epoch	Step	Ter	Bleu	Cer	Validation Loss
1.5521	0.1777	1000	81.7420	21.5248	0.8951	1.5182
1.439	0.3554	2000	80.7229	22.3451	0.9050	1.4391
1.3655	0.5330	3000	87.8504	21.8106	0.9637	1.3942
1.3337	0.7107	4000	72.3619	25.0372	0.8021	1.3678
1.28	0.8884	5000	70.3694	26.0819	0.7884	1.3418
1.2317	1.0661	6000	67.9539	26.4508	0.7525	1.3320
1.2091	1.2438	7000	72.6683	25.6745	0.7929	1.3200
1.1952	1.4215	8000	72.6511	25.8194	0.8057	1.3073
1.1857	1.5991	9000	67.1112	27.2554	0.7399	1.2972
1.1555	1.7768	10000	68.6435	26.6595	0.7507	1.2923
1.1365	1.9545	11000	72.0728	25.8930	0.8009	1.2863
1.0942	2.1322	12000	73.6290	25.7207	0.8342	1.2930
1.0913	2.3099	13000	67.5692	27.2751	0.7503	1.2845
1.0692	2.4876	14000	67.2935	27.5690	0.7462	1.2808
1.0634	2.6652	15000	67.1187	27.2263	0.7345	1.2874
1.0649	2.8429	16000	70.4142	26.6793	0.8115	1.2705
1.0156	3.0206	17000	67.4840	27.2707	0.7497	1.2726
1.0133	3.1983	18000	61.5766	28.8771	0.6753	1.2796
0.9918	3.3760	19000	63.9367	28.2497	0.7048	1.2773
0.9873	3.5537	20000	64.1168	28.4087	0.7027	1.2751
0.9855	3.7313	21000	63.6902	28.3099	0.7012	1.2770
0.9786	3.9090	22000	65.1411	28.0547	0.7137	1.2705
0.9503	4.0867	23000	66.0555	27.5599	0.7328	1.2769
0.9545	4.2644	24000	63.5736	28.3790	0.6966	1.2777
0.9513	4.4421	25000	62.5396	28.6578	0.6887	1.2747
0.9353	4.6198	26000	65.2240	27.9274	0.7189	1.2741
0.9367	4.7974	27000	62.8048	28.5189	0.6891	1.2757
0.9368	4.9751	28000	65.2725	27.8943	0.7231	1.2715
0.9146	5.1528	29000	63.4137	28.4151	0.6955	1.2780
0.9063	5.3305	30000	62.2916	28.8933	0.6899	1.2770
0.8982	5.5082	31000	60.7211	29.1959	0.6731	1.2819
0.902	5.6859	32000	61.1492	29.2606	0.6708	1.2786
0.9078	5.8635	33000	61.9583	28.9441	0.6796	1.2799
0.8972	6.0412	34000	61.3061	29.0500	0.6726	1.2826
0.9012	6.2189	35000	61.9568	28.9005	0.6806	1.2848
0.8954	6.3966	36000	61.0618	29.1654	0.6672	1.2822
0.8896	6.5743	37000	60.4828	29.3658	0.6602	1.2812

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu128
Datasets 4.0.0
Tokenizers 0.21.2

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Languages: ja, zh
Created: Apr 27, 2026
Updated: Apr 27, 2026