whisper-small-pashto Open-source Speech Recognition Model - Free Deployment for Accurate Pashto Speech Recognition

Home

Whisper Small Pashto

Developed by ihanif

A Pashto (ps) speech recognition model fine-tuned based on OpenAI Whisper-small, trained on the FLEURS dataset

Speech Recognition

Transformers

OtherOpen Source License:Apache-2.0 #Pashto speech recognition #Low-resource language ASR #Whisper fine-tuned model

Downloads 18

Release Time : 12/9/2022

Model Overview

This model is an optimized automatic speech recognition (ASR) model for Pashto, fine-tuned based on the Whisper-small architecture, suitable for Pashto speech-to-text tasks

Model Features

Pashto Optimization

Specially fine-tuned for Pashto, offering better language adaptability compared to the original Whisper model

Based on Whisper Architecture

Utilizes the OpenAI Whisper-small architecture with robust foundational speech recognition capabilities

Trained on FLEURS Dataset

Trained and evaluated using the ps_af configuration data from the google/fleurs dataset

Model Capabilities

Pashto speech recognition

Speech-to-text

Automatic Speech Recognition

Use Cases

Speech Transcription

Pashto Speech Transcription

Convert Pashto speech content into text

Word Error Rate (WER) 63.1%

Voice Assistants

Pashto Voice Command Recognition

Used as a speech recognition component for Pashto voice assistants or interactive systems

🚀 Whisper Small Pashto

This is a fine - tuned model based on openai/whisper-small, trained on the google/fleurs ps_af dataset for automatic speech recognition.

🚀 Quick Start

This model is a fine - tuned version of openai/whisper-small on the google/fleurs ps_af dataset. It achieves the following results on the evaluation set:

Loss: 1.1800
Wer: 63.1053

📚 Documentation

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: 3e - 07
train_batch_size: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
training_steps: 5200
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.0871	14.29	100	2.0102	230.2739
1.465	28.57	200	1.4969	137.2427
1.1617	42.86	300	1.2716	76.3242
1.0019	57.14	400	1.1645	71.3756
0.9052	71.43	500	1.1051	69.7866
0.8334	85.71	600	1.0691	68.2657
0.7838	100.0	700	1.0483	67.1686
0.7539	114.29	800	1.0363	66.4195
0.7377	128.57	900	1.0297	66.2001
0.7325	142.86	1000	1.0277	66.0033
0.6952	157.14	1100	1.0122	65.0575
0.6531	171.43	1200	1.0014	64.4219
0.6189	185.71	1300	0.9945	63.7939
0.5993	200.0	1400	0.9896	63.3550
0.5757	214.29	1500	0.9864	63.2264
0.5601	228.57	1600	0.9845	62.9162
0.5482	242.86	1700	0.9833	62.8178
0.5382	257.14	1800	0.9827	62.8405
0.5325	271.43	1900	0.9823	62.7648
0.5287	285.71	2000	0.9822	62.8178
0.3494	357.14	2500	1.0026	61.6147
0.2287	428.57	3000	1.0533	61.5163
0.1525	500.0	3500	1.1041	62.0536
0.1089	571.43	4000	1.1451	62.5076
0.0871	642.86	4500	1.1704	62.9313
0.0797	714.29	5000	1.1791	63.1659
0.0799	728.57	5100	1.1800	63.1053
0.0791	742.86	5200	1.1803	63.1129

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2

📄 License

This model 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