Model Card for ArTST_v2

ArTST (ASR task)

ArTST model finetuned for automatic speech recognition (speech-to-text) on MGB2.

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

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

tokenizer = SpeechT5Tokenizer.from_pretrained("mbzuai/artst_asr_v2")
processor = SpeechT5Processor.from_pretrained("mbzuai/artst_asr_v2" , tokenizer=tokenizer)
model = SpeechT5ForSpeechToText.from_pretrained("mbzuai/artst_asr_v2").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=250)

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

Usage with Pipeline

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline

device = "cuda"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "MBZUAI/artst_asr_v2"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device)
pipe = pipeline(
 "automatic-speech-recognition",
 model=model,
 tokenizer=processor.tokenizer,
 feature_extractor=processor.feature_extractor,
 torch_dtype=torch_dtype,
 device=device,
)

audio , sr = sf.read("path/to/audio/file")
if sr != 16000: 
 audio = librosa.resample(audio), orig_sr=sr, target_sr=16000)
result = pipe(audio)
print(result['text'])

Model Sources [optional]

• Repository: github
• Paper : Arxiv

Citation [optional]

BibTeX:

@misc{djanibekov2024dialectalcoveragegeneralizationarabic,
 title={Dialectal Coverage And Generalization in Arabic Speech Recognition}, 
 author={Amirbek Djanibekov and Hawau Olamide Toyin and Raghad Alshalan and Abdullah Alitr and Hanan Aldarmaki},
 year={2024},
 eprint={2411.05872},
 archivePrefix={arXiv},
 primaryClass={cs.CL},
 url={https://arxiv.org/abs/2411.05872}, 
}

@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",
}