wav2vec2-base-north-vi

minhtien2405/wav2vec2-base-north-vi

wav2vec2-base-north-vi is a automatic speech recognition model from minhtien2405. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

5% of all-time downloads

All-time downloads

193

Public

Parameters

94.5M

54.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors378 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: cc-by-nc-4.0
Model type: wav2vec2
Access: Public
Created: Jul 8, 2025
Updated: Jul 9, 2025
SHA: c549d78e

Base models

nguyenvulebinh/wav2vec2-base-vietnamese-250h

Model card

From the Hugging Face model README

wav2vec2-base-north-vi

This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vietnamese-250h on the nguyendv02/ViMD_Dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.3268
Wer: 0.1288

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: 0.0003
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2171	0.2164	40	0.3531	0.2336
0.527	0.4327	80	0.3674	0.1767
0.5245	0.6491	120	0.3467	0.1967
0.5189	0.8654	160	0.3635	0.1812
0.4589	1.0811	200	0.3410	0.1807
0.442	1.2975	240	0.3382	0.1764
0.4528	1.5139	280	0.3404	0.1713
1.1344	1.7302	320	0.3403	0.1843
0.4726	1.9466	360	0.3365	0.1762
0.475	2.1623	400	0.3442	0.1729
0.4345	2.3786	440	0.3317	0.1706
0.4249	2.5950	480	0.3149	0.1769
0.4385	2.8114	520	0.3281	0.1646
1.119	3.0270	560	0.3422	0.1613
0.4082	3.2434	600	0.3449	0.1680
1.0262	3.4598	640	0.3459	0.1630
0.411	3.6761	680	0.3157	0.1744
0.3922	3.8925	720	0.3347	0.1672
0.408	4.1082	760	0.3260	0.1619
0.3922	4.3245	800	0.3212	0.1718
0.4002	4.5409	840	0.3212	0.2031
0.399	4.7573	880	0.3207	0.1677
0.418	4.9736	920	0.3392	0.1605
0.379	5.1893	960	0.3145	0.1718
0.3729	5.4057	1000	0.3234	0.1665
0.3675	5.6220	1040	0.3262	0.1663
0.3941	5.8384	1080	0.3375	0.1580
0.3763	6.0541	1120	0.3199	0.1701
0.3567	6.2705	1160	0.3267	0.1651
0.3521	6.4868	1200	0.3184	0.1572
0.3464	6.7032	1240	0.3357	0.1621
0.3413	6.9195	1280	0.3094	0.1590
0.3563	7.1352	1320	0.3343	0.1600
0.356	7.3516	1360	0.3285	0.1561
0.3599	7.5680	1400	0.3299	0.1573
0.3497	7.7843	1440	0.3299	0.1540
0.8469	8.0	1480	0.3199	0.1549
0.3352	8.2164	1520	0.3173	0.1670
0.3362	8.4327	1560	0.3256	0.1550
0.3468	8.6491	1600	0.3241	0.1615
0.3352	8.8654	1640	0.3219	0.1580
0.3588	9.0811	1680	0.3256	0.1534
0.3077	9.2975	1720	0.3384	0.1564
0.3169	9.5139	1760	0.3272	0.1495
0.3406	9.7302	1800	0.3249	0.1553
0.3341	9.9466	1840	0.3250	0.1531
0.3071	10.1623	1880	0.3522	0.1493
0.2924	10.3786	1920	0.3201	0.1553
0.3378	10.5950	1960	0.3238	0.1528
0.3234	10.8114	2000	0.3344	0.1555
0.3143	11.0270	2040	0.3269	0.1558
0.3023	11.2434	2080	0.3220	0.1565
0.2961	11.4598	2120	0.3187	0.1721
0.2995	11.6761	2160	0.3464	0.1527
0.3251	11.8925	2200	0.3225	0.1539
0.3395	12.1082	2240	0.3360	0.1539
0.3158	12.3245	2280	0.3173	0.1496
0.311	12.5409	2320	0.3302	0.1473
0.284	12.7573	2360	0.3399	0.1500
0.3092	12.9736	2400	0.3245	0.1509
0.3245	13.1893	2440	0.3281	0.1503
0.3889	13.4057	2480	0.3419	0.1495
0.2609	13.6220	2520	0.3403	0.1480
0.2769	13.8384	2560	0.3264	0.1483
0.2643	14.0541	2600	0.3315	0.1574
0.2804	14.2705	2640	0.3357	0.1489
0.2668	14.4868	2680	0.3186	0.1456
0.2739	14.7032	2720	0.3407	0.1492
0.263	14.9195	2760	0.3306	0.1491
0.2582	15.1352	2800	0.3307	0.1473
0.2787	15.3516	2840	0.3310	0.1520
0.276	15.5680	2880	0.3270	0.1486
0.2758	15.7843	2920	0.3370	0.1471
0.292	16.0	2960	0.3456	0.1451
0.2643	16.2164	3000	0.3384	0.1499
0.2707	16.4327	3040	0.3460	0.1444
0.2606	16.6491	3080	0.3355	0.1462
0.2554	16.8654	3120	0.3534	0.1441
0.2484	17.0811	3160	0.3466	0.1517
0.231	17.2975	3200	0.3353	0.1454
0.2502	17.5139	3240	0.3406	0.1464
0.2574	17.7302	3280	0.3347	0.1451
0.2339	17.9466	3320	0.3430	0.1490
0.2305	18.1623	3360	0.3472	0.1476
0.2415	18.3786	3400	0.3393	0.1455
0.2579	18.5950	3440	0.3396	0.1466
0.254	18.8114	3480	0.3443	0.1436
0.2292	19.0270	3520	0.3503	0.1454
0.2358	19.2434	3560	0.3547	0.1447
0.231	19.4598	3600	0.3545	0.1436
0.2542	19.6761	3640	0.3432	0.1426
0.2466	19.8925	3680	0.3539	0.1403
0.2367	20.1082	3720	0.3458	0.1453
0.2196	20.3245	3760	0.3460	0.1412
0.2126	20.5409	3800	0.3539	0.1466
0.2254	20.7573	3840	0.3561	0.1400
0.2301	20.9736	3880	0.3446	0.1428
0.2157	21.1893	3920	0.3542	0.1432
0.2157	21.4057	3960	0.3557	0.1400
0.2172	21.6220	4000	0.3438	0.1408
0.1969	21.8384	4040	0.3538	0.1451
0.2001	22.0541	4080	0.3578	0.1415
0.23	22.2705	4120	0.3501	0.1414
0.2285	22.4868	4160	0.3622	0.1403
0.2049	22.7032	4200	0.3649	0.1397
0.2228	22.9195	4240	0.3602	0.1391
0.2393	23.1352	4280	0.3624	0.1386
0.2116	23.3516	4320	0.3548	0.1374
0.256	23.5680	4360	0.3536	0.1399
0.2157	23.7843	4400	0.3670	0.1380
0.2155	24.0	4440	0.3596	0.1399
0.1938	24.2164	4480	0.3637	0.1407
0.1972	24.4327	4520	0.3733	0.1372
0.2142	24.6491	4560	0.3579	0.1399
0.2092	24.8654	4600	0.3647	0.1361
0.3059	25.0811	4640	0.3707	0.1387
0.2014	25.2975	4680	0.3723	0.1352
0.2116	25.5139	4720	0.3629	0.1374
0.1854	25.7302	4760	0.3624	0.1371
0.2074	25.9466	4800	0.3873	0.1345
0.2034	26.1623	4840	0.3603	0.1376
0.1893	26.3786	4880	0.3761	0.1369
0.1859	26.5950	4920	0.3737	0.1354
0.2076	26.8114	4960	0.3528	0.1372
0.1879	27.0270	5000	0.3657	0.1356
0.1927	27.2434	5040	0.3637	0.1351
0.2059	27.4598	5080	0.3789	0.1341
0.1751	27.6761	5120	0.3671	0.1355
0.1864	27.8925	5160	0.3657	0.1348
0.1822	28.1082	5200	0.3653	0.1358
0.1955	28.3245	5240	0.3719	0.1356
0.194	28.5409	5280	0.3706	0.1360
0.1888	28.7573	5320	0.3700	0.1358
0.1954	28.9736	5360	0.3664	0.1347
0.1897	29.1893	5400	0.3687	0.1350
0.1851	29.4057	5440	0.3664	0.1356
0.182	29.6220	5480	0.3674	0.1354
0.187	29.8384	5520	0.3651	0.1348

Framework versions

Transformers 4.53.0
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.2

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: cc-by-nc-4.0
Languages: vi
Created: Jul 8, 2025
Updated: Jul 9, 2025