Overview

The Sinhala Audio to Text model provides a specialized speech-to-text pipeline for the Sinhala language, addressing a critical gap in regional language support for developers. Unlike generic multilingual models that often struggle with the specific phonetic nuances of Sinhala, this model is optimized for higher transcription accuracy in native contexts. It is particularly useful for building accessibility tools, automated captioning services, or voice-driven interfaces for the Sri Lankan market. With an Apache-2.0 license, it offers significant flexibility for commercial integration. Developers can integrate this into their existing backend workflows to convert raw audio streams into structured text for downstream NLP tasks like sentiment analysis or translation.

Highlights

High-accuracy transcription for native Sinhala speech
Permissive Apache-2.0 license for commercial use
Ideal for regional accessibility and captioning tools
Streamlines audio-to-text pipelines for Sri Lankan markets

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("AqeelShafy7/Sinhala-Audio_to_Text")
tokenizer = AutoTokenizer.from_pretrained("AqeelShafy7/Sinhala-Audio_to_Text")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download AqeelShafy7/Sinhala-Audio_to_Text

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download AqeelShafy7/Sinhala-Audio_to_Text config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('AqeelShafy7/Sinhala-Audio_to_Text')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/AqeelShafy7/Sinhala-Audio_to_Text

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/AqeelShafy7/Sinhala-Audio_to_Text

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('AqeelShafy7/Sinhala-Audio_to_Text')
tokenizer = AutoTokenizer.from_pretrained('AqeelShafy7/Sinhala-Audio_to_Text')