MBZUAI / artst-v2-asr

ArTST-V2 (ASR task)

ArTST model finetuned for automatic speech recognition (speech-to-text) on QASR to improve dialectal generalization.

Model Description

• Developed by: Speech Lab, MBZUAI
• Model type: SpeechT5
• Language: Arabic
• Finetuned from: ArTST-v2 pretrained

How to Get Started with the Model

import soundfile as sf
from transformers import (
    SpeechT5Config,
    SpeechT5FeatureExtractor,
    SpeechT5ForSpeechToText,
    SpeechT5Processor,
    SpeechT5Tokenizer,
)

from custom_tokenizer import CustomTextTokenizer

device = "cuda" if torch.cuda.is_available() else "CPU"

model_id = "mbzuai/artst-v2-asr"

tokenizer = SpeechT5Tokenizer.from_pretrained(model_id)
processor = SpeechT5Processor.from_pretrained(model_id , tokenizer=tokenizer)
model = SpeechT5ForSpeechToText.from_pretrained(model_id).to(device)

audio, sr = sf.read("audio.wav")

inputs = processor(audio=audio, sampling_rate=sr, return_tensors="pt")
predicted_ids = model.generate(**inputs.to(device), max_length=150)

transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
print(transcription[0])

Model Sources [optional]

• Repository: github
• Paper : pre-print

Citation [optional]

BibTeX:

@inproceedings{toyin-etal-2023-artst,
    title = "{A}r{TST}: {A}rabic Text and Speech Transformer",
    author = "Toyin, Hawau  and
      Djanibekov, Amirbek  and
      Kulkarni, Ajinkya  and
      Aldarmaki, Hanan",
    booktitle = "Proceedings of ArabicNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.arabicnlp-1.5",
    doi = "10.18653/v1/2023.arabicnlp-1.5",
    pages = "41--51",
}