wav2vec2-xls-r-300m-cv7-istech

FatihC06/wav2vec2-xls-r-300m-cv7-istech

wav2vec2-xls-r-300m-cv7-istech is a automatic speech recognition model from FatihC06. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

25% of all-time downloads

All-time downloads

120

Public

Parameters

315M

20.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Jan 9, 2025
Updated: Jan 10, 2025
SHA: f20da185

Base models

facebook/wav2vec2-xls-r-300m

Model card

From the Hugging Face model README

wav2vec2-xls-r-300m-cv7-istech

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7978
Wer: 0.7496

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: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
11.1946	0.0803	20	6.7455	1.0
5.1957	0.1606	40	3.7715	1.0
3.5889	0.2410	60	3.4781	1.0
3.3656	0.3213	80	3.3373	1.0
3.5262	0.4016	100	3.3093	1.0
3.1816	0.4819	120	3.2444	1.0
3.3344	0.5622	140	3.2887	1.0
3.2522	0.6426	160	3.2321	1.0
3.1819	0.7229	180	3.2538	1.0
3.3665	0.8032	200	3.2018	1.0
3.1257	0.8835	220	3.1751	1.0
3.2982	0.9639	240	3.1929	1.0
3.2181	1.0442	260	3.1781	1.0
3.1455	1.1245	280	3.3508	1.0
3.2722	1.2048	300	3.2343	1.0
3.1217	1.2851	320	3.1378	0.9999
3.2419	1.3655	340	3.2108	0.9999
3.1825	1.4458	360	3.1363	0.9999
3.1316	1.5261	380	3.1685	0.9999
3.2373	1.6064	400	3.1731	1.0
3.0634	1.6867	420	3.1083	0.9999
3.1367	1.7671	440	3.1582	0.9999
3.0831	1.8474	460	3.0410	0.9999
2.9524	1.9277	480	2.9578	0.9999
3.1076	2.0080	500	2.9558	0.9999
2.8085	2.0884	520	2.8155	0.9999
2.7768	2.1687	540	2.8155	0.9998
2.6186	2.2490	560	2.5386	1.0
2.3452	2.3293	580	2.3387	0.9994
2.4213	2.4096	600	2.2745	0.9997
1.8149	2.4900	620	1.8076	0.9906
1.747	2.5703	640	1.8517	0.9962
1.6369	2.6506	660	1.4838	0.9662
1.3732	2.7309	680	1.4990	0.9852
1.6638	2.8112	700	1.3854	0.9383
1.1034	2.8916	720	1.2258	0.9112
1.3003	2.9719	740	1.3696	0.9174
1.2128	3.0522	760	1.1576	0.8966
0.9759	3.1325	780	1.1325	0.8838
1.2551	3.2129	800	1.1489	0.8831
0.8371	3.2932	820	1.0224	0.8460
1.0434	3.3735	840	1.0927	0.8680
1.0386	3.4538	860	0.9731	0.8383
0.879	3.5341	880	0.9916	0.8428
1.1771	3.6145	900	0.9857	0.8406
0.6948	3.6948	920	0.9493	0.8203
0.9657	3.7751	940	0.9960	0.8364
0.8991	3.8554	960	0.8949	0.8013
0.7712	3.9357	980	0.9039	0.8096
1.0684	4.0161	1000	0.9024	0.8012
0.5559	4.0964	1020	0.8611	0.7872
0.8446	4.1767	1040	0.9017	0.8021
0.7911	4.2570	1060	0.8596	0.7848
0.6178	4.3373	1080	0.8612	0.7778
0.9147	4.4177	1100	0.8654	0.7756
0.5448	4.4980	1120	0.8222	0.7649
0.7812	4.5783	1140	0.8337	0.7697
0.6784	4.6586	1160	0.8146	0.7588
0.6022	4.7390	1180	0.8077	0.7538
0.8592	4.8193	1200	0.8121	0.7621
0.4884	4.8996	1220	0.7982	0.7487
0.7429	4.9799	1240	0.7978	0.7496

Framework versions

Transformers 4.45.2
Pytorch 2.5.1
Datasets 2.19.1
Tokenizers 0.20.1

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: Jan 9, 2025
Updated: Jan 10, 2025