Instructions to use Jakir057/BanglaIPA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use Jakir057/BanglaIPA with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy), and from_pretrained_keras was removed in huggingface_hub 1.0. # See https://github.com/keras-team/tf-keras for more details. # !pip install "huggingface_hub<1.0" tf_keras from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("Jakir057/BanglaIPA") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signaturea526474 -
Update README.md
Verified signature87299b5 -
Update README.md
Verified signature<div align="center"> <h1>🚨 BanglaIPA 🚨 BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali </h1> 📝 <a href="https://arxiv.org/abs/2601.01778v1"><b>Paper</b></a>, 🖥️ <a href="https://github.com/Jak57/BanglaIPA"><b>Github</b></a> </div> **BanglaIPA** - Bengali text to International Phonetic Alphabet (IPA) transcription system is trained on standard Bengali and six regional dialects of Bangladesh using the <a href="https://arxiv.org/abs/2403.20084">DUAL-IPA</a> dataset from Bengali.AI. ## Load the BanglaIPA System **Prerequisite**<br> ``` !pip install tensorflow ``` **Log in to HuggingFace**<br> ```python from huggingface_hub import login login("TOKEN") ``` **Load base model and BRDialect**<br> ```python ## BRDialect from huggingface_hub import hf_hub_download kenlm_model_path = hf_hub_download(repo_id="Jakir057/BRDialect", filename="BRDialect/5gram_kenlm.arpa") state_dict_path = hf_hub_download(repo_id="Jakir057/BRDialect", filename="BRDial…90416b6 -
Upload 4 files
Verified signatureb35ce6f -
initial commit
Verified signature503fa17