wav2vec2-common_voice-tr-demo-dist Open-source Speech Recognition Model

Wav2vec2 Common Voice Tr Demo Dist

Developed by cromz22

This model is an automatic speech recognition (ASR) model fine-tuned on the COMMON_VOICE - TR Turkish dataset based on facebook/wav2vec2-large-xlsr-53, achieving a word error rate of 0.3242 on the evaluation set.

Speech Recognition

Transformers

OtherOpen Source License:Apache-2.0 #Turkish Speech Recognition #Multi-GPU Training #Low Word Error Rate

Downloads 26

Release Time : 5/18/2022

Model Overview

An automatic speech recognition model for Turkish, fine-tuned based on the wav2vec2 architecture, suitable for converting Turkish speech to text.

Model Features

Turkish Language Optimization

Specifically fine-tuned for Turkish speech data, performing well on Turkish recognition tasks.

Based on wav2vec2 Architecture

Uses facebook's wav2vec2-large-xlsr-53 as the base model, featuring powerful speech feature extraction capabilities.

Multi-GPU Training

Utilizes 4 GPUs for distributed training, improving training efficiency.

Model Capabilities

Turkish Speech Recognition

Speech-to-Text

Use Cases

Speech Transcription

Turkish Speech Transcription

Convert Turkish speech content into text

Word Error Rate 0.3242

Voice Assistants

Turkish Voice Command Recognition

Used for voice command recognition in Turkish voice assistant systems

🚀 wav2vec2-common_voice-tr-demo-dist

This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - TR dataset, achieving specific results on the evaluation set.

🚀 Quick Start

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - TR dataset. It achieves the following results on the evaluation set:

Loss: 0.3848
Wer: 0.3242

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi - GPU
num_devices: 4
total_train_batch_size: 16
total_eval_batch_size: 32
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
3.5279	0.46	100	3.6260	1.0
3.1065	0.92	200	3.0854	0.9999
1.4111	1.38	300	1.3343	0.8839
0.8468	1.83	400	0.6920	0.6826
0.6242	2.29	500	0.6001	0.5996
0.4181	2.75	600	0.5655	0.5680
0.4311	3.21	700	0.4478	0.5003
0.3601	3.67	800	0.4548	0.5011
0.2756	4.13	900	0.4444	0.4682
0.2373	4.59	1000	0.4111	0.4432
0.1831	5.05	1100	0.4178	0.4447
0.2423	5.5	1200	0.3881	0.4277
0.2128	5.96	1300	0.3865	0.4018
0.1256	6.42	1400	0.3818	0.4137
0.1038	6.88	1500	0.3739	0.3942
0.1662	7.34	1600	0.3938	0.3929
0.198	7.8	1700	0.3831	0.3837
0.0728	8.26	1800	0.3910	0.3867
0.123	8.72	1900	0.3722	0.3735
0.0776	9.17	2000	0.3938	0.3725
0.1597	9.63	2100	0.3786	0.3697
0.1124	10.09	2200	0.3947	0.3590
0.0965	10.55	2300	0.3952	0.3562
0.0612	11.01	2400	0.3810	0.3476
0.0764	11.47	2500	0.3734	0.3507
0.0973	11.93	2600	0.3935	0.3472
0.0649	12.39	2700	0.3672	0.3413
0.0542	12.84	2800	0.3732	0.3369
0.087	13.3	2900	0.3833	0.3458
0.0196	13.76	3000	0.3761	0.3303
0.0548	14.22	3100	0.3855	0.3274
0.0577	14.68	3200	0.3893	0.3238

Framework versions

Transformers 4.20.0.dev0
Pytorch 1.11.0+cu102
Datasets 2.2.1
Tokenizers 0.12.1

📄 License

This project is licensed under the Apache - 2.0 license.

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