Indian-Accent-English-Whisper-Finetuned Open-Source Model - Accurately recognize Indian English-accented speech!

Indian Accent English Whisper Finetuned

Developed by Tejveer12

Fine-tuned the openai/whisper-large-v3-turbo based on the Indian English accent dataset, which is more suitable for speech recognition of Indian English accents.

Speech Recognition

Transformers

EnglishOpen Source License:MIT #Indian English speech recognition #Accent optimization #Low word error rate

Downloads 1,733

Release Time : 3/8/2025

Model Overview

This model is an automatic speech recognition model optimized for Indian English accents, showing a low word error rate on the evaluation set.

Model Features

Optimization for Indian English accents

Specifically fine-tuned for Indian English accents to improve recognition accuracy

Low word error rate

Achieved a word error rate (WER) of 7.5056 on the evaluation set, showing excellent performance

Based on the Whisper architecture

Fine-tuned based on the openai/whisper-large-v3-turbo model, inheriting its powerful performance

Model Capabilities

Indian English speech recognition

Automatic speech-to-text conversion

English accent adaptation

Use Cases

Speech transcription

Indian English meeting records

Convert meeting recordings with Indian English accents into text records

High-accuracy text transcription

Customer service voice analysis

Analyze the voice feedback of Indian English customers

Improve customer service efficiency and analysis accuracy

🚀 Whisper Indian English Accent

This model is a fine - tuned version of openai/whisper - large - v3 - turbo on the Indian English Accent dataset. It offers high - accuracy speech recognition for Indian English accents, providing valuable support for related speech - to - text applications.

🚀 Quick Start

This model is a fine - tuned version of openai/whisper - large - v3 - turbo on the Indian English Accent dataset. It achieves the following results on the evaluation set:

Loss: 0.2065
Wer: 7.5056

📚 Documentation

Model Information

Property	Details
Model Type	Whisper Indian English Accent
Base Model	openai/whisper - large - v3 - turbo
Tags	generated_from_trainer
Datasets	WillHeld/india_accent_cv
Metrics	wer

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: 1e - 05
train_batch_size: 16
eval_batch_size: 8
seed: 42
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: 500
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.342	0.1943	1000	0.3226	14.1310
0.2741	0.3885	2000	0.3130	13.9553
0.2576	0.5828	3000	0.2967	12.9931
0.2825	0.7770	4000	0.2692	12.3390
0.2295	0.9713	5000	0.2565	11.8331
0.1489	1.1655	6000	0.2498	11.6933
0.1485	1.3598	7000	0.2452	11.1411
0.1385	1.5540	8000	0.2346	10.4428
0.1253	1.7483	9000	0.2254	10.1852
0.1297	1.9425	10000	0.2144	9.7109
0.0594	2.1368	11000	0.2174	9.5363
0.0629	2.3310	12000	0.2136	9.8276
0.0654	2.5253	13000	0.2102	9.4301
0.0625	2.7195	14000	0.2075	8.9432
0.0574	2.9138	15000	0.2009	8.7802
0.0276	3.1080	16000	0.2050	8.4594
0.0251	3.3023	17000	0.2046	8.5951
0.0246	3.4965	18000	0.2035	8.1187
0.0259	3.6908	19000	0.2002	8.0588
0.021	3.8850	20000	0.1951	7.9147
0.0072	4.0793	21000	0.2053	7.7548
0.0067	4.2735	22000	0.2085	7.4972
0.0067	4.4678	23000	0.2094	7.6970
0.0062	4.6620	24000	0.2071	7.7433
0.0046	4.8563	25000	0.2065	7.5056

Framework versions

Transformers 4.49.0
Pytorch 2.2.0a0 + 81ea7a4
Datasets 3.3.2
Tokenizers 0.21.0

📄 License

This model is released under the MIT 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