README.md

---
library_name: Nvidia Nemo
license: apache-2.0
language:
- fa
pipeline_tag: automatic-speech-recognition
tags:
- Persian
- Neura
- PersianASR
datasets: 
- common_voice_17_0
---
# Neura Speech Nemo

<p align="center">
  <img src="neura_speech.png" width=512 height=256 />
</p>

<!-- Provide a quick summary of what the model is/does. -->

## Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** Neura company
- **Funded by:** Neura
- **Model type:** fa_FastConformers_Transducer
- **Language(s) (NLP):** Persian

## Model Architecture

This model uses a FastConformer-TDT architecture. FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling.
You may find more information on the details of FastConformer here: Fast-Conformer Model.
[Fast Conformer with Linearly Scalable Attention for Efficient
Speech Recognition](https://arxiv.org/abs/2305.05084).

## Uses
Check out the Google Colab demo to run NeuraSpeech ASR on a free-tier Google Colab instance: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kt34iFb_ez0y2SjU_km3vnzG4ccdVrXB#scrollTo=Z9DvUwmKtmR7)



make sure these packages are installed:
```
!pip install nemo_toolkit['all']
```
```python
from IPython.display import Audio, display
display(Audio('persian_audio.mp3', rate = 32_000,autoplay=True))
```

```python
import nemo
print('nemo', nemo.__version__)
import numpy as np
import nemo.collections.asr as nemo_asr

asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained(model_name="Neurai/NeuraSpeech_900h")
asr_model.transcribe(paths2audio_files=['persian_audio.mp3', ], batch_size=1)[0]

```
trascribed text :
```
او خواهان آزاد کردن بردگان بود
```


## More Information
https://neura.info

## Model Card Authors
Esmaeil Zahedi, Mohsen Yazdinejad

## Model Card Contact
info@neura.info