wavlm-vindata-demo-dist Open-Source Automatic Speech Recognition Model - Accurately Identify Vietnamese Speech Information

Home

Wavlm Vindata Demo Dist

Developed by phongdtd

An automatic speech recognition model fine-tuned on Vietnamese datasets based on microsoft/wavlm-base

Speech Recognition

Transformers

#Vietnamese speech recognition #WavLM fine-tuning #Low word error rate

Downloads 17

Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model based on the WavLM architecture, specifically fine-tuned for Vietnamese speech recognition tasks.

Model Features

Optimized for Vietnamese speech recognition

Specially fine-tuned on Vietnamese datasets and optimized for Vietnamese speech characteristics

Based on WavLM architecture

Utilizes Microsoft's WavLM-base as the foundation model, featuring robust speech representation capabilities

Multi-GPU training

Employs distributed multi-GPU training to enhance training efficiency

Model Capabilities

Vietnamese speech-to-text

Continuous speech recognition

Speech content understanding

Use Cases

Speech transcription

Vietnamese meeting minutes

Automatically transcribe Vietnamese meeting recordings into written records

Voice assistant

Provide speech recognition capabilities for Vietnamese voice assistants

Media processing

Video subtitle generation

Automatically generate subtitles for Vietnamese video content

🚀 wavlm-vindata-demo-dist

This model is a fine - tuned version of microsoft/wavlm-base on the PHONGDTD/VINDATAVLSP - NA dataset. It offers a practical solution for automatic speech recognition tasks, leveraging the pre - trained capabilities of the base model and adapting them to the specific dataset. The model achieves the following results on the evaluation set:

Loss: 3.4439
Wer: 1.0

🚀 Quick Start

This model can be used directly in speech recognition tasks. You can load the model through the Hugging Face Transformers library and start inference.

📚 Documentation

Model description

This model is a fine - tuned version of microsoft/wavlm-base on the PHONGDTD/VINDATAVLSP - NA dataset.

Intended uses & limitations

The model is mainly used for automatic speech recognition tasks. However, more information about its limitations needs to be further explored.

Training and evaluation data

The model is trained on the PHONGDTD/VINDATAVLSP - NA dataset. But more detailed information about the data needs to be provided.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi - GPU
num_devices: 2
total_train_batch_size: 2
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 15.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.0704	0.01	100	3.8768	1.0
3.6236	0.01	200	3.4611	1.0
6.597	0.02	300	3.4557	1.0
3.4744	0.03	400	3.4567	1.0
5.3992	0.04	500	3.4631	1.0
4.5348	0.04	600	3.4651	1.0
3.2457	0.05	700	3.4917	1.0
3.9245	0.06	800	3.4680	1.0
3.2904	0.07	900	3.4518	1.0
3.4768	0.07	1000	3.4506	1.0
3.2418	0.08	1100	3.4474	1.0
3.3111	0.09	1200	3.4684	1.0
3.986	0.09	1300	3.4465	1.0
4.3206	0.1	1400	3.4723	1.0
4.682	0.11	1500	3.4732	1.0
4.858	0.12	1600	3.4416	1.0
3.2949	0.12	1700	3.4481	1.0
3.4435	0.13	1800	3.4570	1.0
5.0695	0.14	1900	3.4448	1.0
3.4962	0.14	2000	3.4416	1.0
3.4891	0.15	2100	3.4455	1.0
4.1281	0.16	2200	3.4447	1.0
3.5956	0.17	2300	3.4512	1.0
3.6312	0.17	2400	3.4484	1.0
4.5383	0.18	2500	3.4435	1.0
6.1329	0.19	2600	3.4530	1.0
3.709	0.2	2700	3.4466	1.0
3.289	0.2	2800	3.4463	1.0
4.3301	0.21	2900	3.4418	1.0
4.6656	0.22	3000	3.4447	1.0
3.4288	0.22	3100	3.4715	1.0
3.5506	0.23	3200	3.4437	1.0
3.7497	0.24	3300	3.4910	1.0
3.5198	0.25	3400	3.4574	1.0
3.4183	0.25	3500	3.4607	1.0
4.5573	0.26	3600	3.4421	1.0
3.5737	0.27	3700	3.4481	1.0
4.9008	0.28	3800	3.4411	1.0
4.8725	0.28	3900	3.4422	1.0
3.5799	0.29	4000	3.4659	1.0
3.3257	0.3	4100	3.4519	1.0
3.6887	0.3	4200	3.4827	1.0
3.3037	0.31	4300	3.4632	1.0
5.5543	0.32	4400	3.4480	1.0
3.2898	0.33	4500	3.4404	1.0
3.2794	0.33	4600	3.4633	1.0
3.7896	0.34	4700	3.4439	1.0
3.6662	0.35	4800	3.4587	1.0
3.588	0.35	4900	3.4520	1.0
4.0535	0.36	5000	3.4450	1.0
3.4335	0.37	5100	3.4577	1.0
3.6317	0.38	5200	3.4443	1.0
5.2564	0.38	5300	3.4505	1.0
3.8781	0.39	5400	3.4418	1.0
4.6269	0.4	5500	3.4425	1.0
3.6095	0.41	5600	3.4581	1.0
4.6164	0.41	5700	3.4404	1.0
3.117	0.42	5800	3.4596	1.0
4.3939	0.43	5900	3.4401	1.0
3.5856	0.43	6000	3.4413	1.0
3.5187	0.44	6100	3.4452	1.0
4.7991	0.45	6200	3.4481	1.0
3.3905	0.46	6300	3.4420	1.0
3.5086	0.46	6400	3.4494	1.0
4.8217	0.47	6500	3.4477	1.0
3.3193	0.48	6600	3.4382	1.0
5.3482	0.49	6700	3.4580	1.0
3.3947	0.49	6800	3.4767	1.0
6.3352	0.5	6900	3.4476	1.0
3.4448	0.51	7000	3.4557	1.0
3.5358	0.51	7100	3.4438	1.0
3.3499	0.52	7200	3.4445	1.0
3.6932	0.53	7300	3.4463	1.0
6.9058	0.54	7400	3.4482	1.0
4.5514	0.54	7500	3.4422	1.0
3.517	0.55	7600	3.4505	1.0
7.4479	0.56	7700	3.4461	1.0
3.3761	0.56	7800	3.4511	1.0
4.5925	0.57	7900	3.4389	1.0
5.2682	0.58	8000	3.4563	1.0
5.6748	0.59	8100	3.4601	1.0
4.4335	0.59	8200	3.4439	1.0
5.1686	0.6	8300	3.4444	1.0
3.5245	0.61	8400	3.4629	1.0
4.9426	0.62	8500	3.4389	1.0
4.4654	0.62	8600	3.4427	1.0
3.5626	0.63	8700	3.4521	1.0
4.7086	0.64	8800	3.4489	1.0
3.238	0.64	8900	3.4478	1.0
4.2738	0.65	9000	3.4510	1.0
3.4468	0.66	9100	3.4411	1.0
3.2292	0.67	9200	3.4416	1.0
3.4972	0.67	9300	3.4643	1.0
7.3434	0.68	9400	3.4587	1.0
3.708	0.69	9500	3.4799	1.0
4.6466	0.69	9600	3.4490	1.0
3.3347	0.7	9700	3.4532	1.0
5.1486	0.71	9800	3.4427	1.0
3.6456	0.72	9900	3.4492	1.0
5.3904	0.72	10000	3.4497	1.0
4.8832	0.73	10100	3.4476	1.0
3.4482	0.74	10200	3.4539	1.0
3.617	0.75	10300	3.4547	1.0
5.4691	0.75	10400	3.4663	1.0
4.2759	0.76	10500	3.4401	1.0
8.2106	0.77	10600	3.4404	1.0
3.4894	0.77	10700	3.4426	1.0
3.6875	0.78	10800	3.4439	1.0
3.3277	0.79	10900	3.4446	1.0
4.5175	0.8	11000	3.4456	1.0
5.2161	0.8	11100	3.4388	1.0
3.5234	0.81	11200	3.4418	1.0
4.2212	0.82	11300	3.4392	1.0
3.6923	0.83	11400	3.4494	1.0
3.4863	0.83	11500	3.4572	1.0
6.3201	0.84	11600	3.4377	1.0
3.7543	0.85	11700	3.4533	1.0
3.3959	0.85	11800	3.4600	1.0
3.5691	0.86	11900	3.4673	1.0
3.49	0.87	12000	3.4407	1.0
7.1165	0.88	12100	3.4427	1.0
6.731	0.88	12200	3.4394	1.0
4.4682	0.89	12300	3.4407	1.0
3.3696	0.9	12400	3.4415	1.0
4.0241	0.9	12500	3.4454	1.0
3.521	0.91	12600	3.4379	1.0
5.5273	0.92	12700	3.4423	1.0
3.4781	0.93	12800	3.4635	1.0
3.4542	0.93	12900	3.4411	1.0
3.2363	0.94	13000	3.4396	1.0
5.3009	0.95	13100	3.4458	1.0
3.498	0.96	13200	3.4398	1.0
6.3325	0.96	13300	3.4514	1.0
3.5368	0.97	13400	3.4437	1.0
5.1164	0.98	13500	3.4623	1.0
3.6144	0.98	13600	3.4512	1.0
6.6018	0.99	13700	3.4493	1.0
3.7539	1.0	13800	3.4597	1.0
3.2903	1.01	13900	3.4813	1.0
3.3243	1.01	14000	3.4510	1.0
3.3485	1.02	14100	3.4389	1.0
3.6197	1.03	14200	3.4519	1.0
3.322	1.04	14300	3.4399	1.0
3.2897	1.04	14400	3.4378	1.0
3.3969	1.05	14500	3.4476	1.0
3.3289	1.06	14600	3.4646	1.0
3.3556	1.06	14700	3.4520	1.0
3.2527	1.07	14800	3.4575	1.0
3.4003	1.08	14900	3.4443	1.0
3.3171	1.09	15000	3.4434	1.0
3.4034	1.09	15100	3.4448	1.0
3.4363	1.1	15200	3.4560	1.0
3.3969	1.11	15300	3.4405	1.0
3.4134	1.11	15400	3.4408	1.0
3.5059	1.12	15500	3.4395	1.0
3.3963	1.13	15600	3.4488	1.0
3.2937	1.14	15700	3.4482	1.0
3.5635	1.14	15800	3.4621	1.0
3.4463	1.15	15900	3.4433	1.0
3.2588	1.16	16000	3.4434	1.0
3.3617	1.17	16100	3.4542	1.0
3.3721	1.17	16200	3.4388	1.0
3.3867	1.18	16300	3.4577	1.0
3.34	1.19	16400	3.4510	1.0
3.3676	1.19	16500	3.4434	1.0
3.5519	1.2	16600	3.4410	1.0
3.3129	1.21	16700	3.4507	1.0
3.3368	1.22	16800	3.4718	1.0
3.3107	1.22	16900	3.4439	1.0
3.2987	1.23	17000	3.4471	1.0
3.3102	1.24	17100	3.4435	1.0
3.2089	1.25	17200	3.4432	1.0
3.415	1.25	17300	3.4472	1.0
3.2884	1.26	17400	3.4388	1.0
3.3837	1.27	17500	3.4444	1.0
3.3181	1.27	17600	3.4438	1.0
3.3071	1.28	17700	3.4406	1.0
3.389	1.29	17800	3.4573	1.0
3.3246	1.3	17900	3.4580	1.0
3.3122	1.3	18000	3.4455	1.0
3.282	1.31	18100	3.4606	1.0
3.2671	1.32	18200	3.4378	1.0
3.3441	1.32	18300	3.4432	1.0
3.3115	1.33	18400	3.4458	1.0
3.3542	1.34	18500	3.4617	1.0
3.3924	1.35	18600	3.4549	1.0
3.4895	1.35	18700	3.4557	1.0
3.4071	1.36	18800	3.4462	1.0
3.3373	1.37	18900	3.4606	1.0
3.3497	1.38	19000	3.4458	1.0
3.3088	1.38	19100	3.4712	1.0
3.333	1.39	19200	3.4483	1.0
3.3773	1.4	19300	3.4455	1.0
3.357	1.4	19400	3.4379	1.0
3.3506	1.41	19500	3.4477	1.0
3.2944	1.42	19600	3.4478	1.0
3.241	1.43	19700	3.4

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご