---
library_name: transformers
tags:
- persian
- whisper-base
- whisper
- farsi
- Neura
- NeuraSpeech
license: apache-2.0
language:
- fa
pipeline_tag: automatic-speech-recognition
---


# 

<p align="center">
  <img src="neura_speech_2.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:** Whisper Base
- **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/12d7zecB94ah7ZHKnDtJF58saLzdkZAj3#scrollTo=oNt032WVkQUa)



make sure these packages are installed:

```python
from IPython.display import Audio, display
display(Audio('persian_audio.mp3', rate = 32_000,autoplay=True))
```

```python
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

# load model and processor
processor = WhisperProcessor.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
model = WhisperForConditionalGeneration.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
forced_decoder_ids = processor.get_decoder_prompt_ids(language="fa", task="transcribe")

array, sample_rate = librosa.load('persian_audio.mp3', sr=16000,mono=True) 
sr = 16000
array = librosa.to_mono(array)
array = librosa.resample(array, orig_sr=sample_rate, target_sr=16000)
input_features = processor(array, sampling_rate=sr, return_tensors="pt").input_features

# generate token ids
predicted_ids = model.generate(input_features)
# decode token ids to text
transcription = processor.batch_decode(predicted_ids,)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
print(transcription)

```
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