Metadata-Version: 2.4
Name: torongoxetu
Version: 1.0.1
Summary: A inference library for the TorongoXetu Assamese ASR model.
Author: Anand Dey
Author-email: ananddey.nic@gmail.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: torch
Requires-Dist: numpy
Requires-Dist: soundfile
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# TorongoXetu Library

`torongoxetu` is a inference library for utilizing the TorongoXetu Assamese Automatic Speech Recognition (ASR) model. It handles model loading, and provides an API for Assamese language transcription.

## Installation

```bash
pip install torongoxetu
```
*(Note: You must install additional dependencies as in requirements.txt from the huggingface torongoXetu model repository)*

## Usage

```python
from torongoxetu import TorongoModel

# 1. Load Model
model = TorongoModel("path/to/torongoXetu-asr.nemo")

# 2. Transcribe File
text = model.transcribe("audio.wav")
print(text)

# 3. Transcribe in Batch or single file
texts = model.transcribe(["file1.wav", "file2.wav"], batch_size=4)
```
