---
license: mit
language:
- ar
---

Here we have model checkpoints, tokenizer and dictionary.

Check out our [github](https://github.com/mbzuai-nlp/ArTST)  for code implementation.
Read our [paper](https://arxiv.org/abs/2310.16621) for more details.


### Pre-Trained Models

 Model | Pre-train Dataset | Model | Tokenizer |
| --- | --- | --- | --- |
| ArTST base | MGB2 | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/pretrain_checkpoint.pt) | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/asr_spm.model)

### Finetuned Models
 Model | FInetune Dataset | Model | Tokenizer |
| --- | --- | --- | --- |
| ArTST ASR | MGB2 | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/MGB2_ASR.pt) | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/asr_spm.model)|
| ArTST TTS | ClArTTS | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/CLARTTS_ArTST_TTS.pt) | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/tts_spm.model)|
| ArTST* TTS |  ClArTTS | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/CLARTTS_ArTSTstar_TTS.pt) | [Hugging Face](https://huggingface.co/MBZUAI/ArTST/blob/main/tts_spm.model)|