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: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]
Uses
N7-BPE-MNI-Tokenizer (Basic Version)
This is the basic version of a Byte-Pair Encoding (BPE) tokenizer trained on Meitei Mayek (Manipuri script) — built to support ASR, NMT, and LLM tasks focused on the mni-Mtei language space.
⚙️ Type:
Tokenizer: BPE
Trained using: tokenizers lib
Language: Meitei (ꯃꯤꯇꯩ ꯃꯌꯦꯛ)
Script: Meitei Mayek only (no Latin/Roman for now)
📦 Use Case:
Perfect for projects in:
🤖 ASR (Automatic Speech Recognition)
🧠 NLP training (T5, GPT, Whisper)
🗣️ TTS training with phoneme alignment
🧩 Any Transformer that allows BPE vocab import
🚀 Plug & Play (with any model that supports custom tokenizers):
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("DayanandaThokchom/N7-BPE-MNI-Tokenizer")
def check_tokenizer_roundtrip(text, src_lang="<mni-Mtei>", tgt_lang="<en>"):
# ⚡ Add language tags
tagged_text = f"{src_lang} {text} {tgt_lang}"
print(f"\n📥 Input Text w/ Lang Tags: {tagged_text}")
token_ids = tokenizer.encode(tagged_text)
print(f"🔢 Token IDs: {token_ids}")
tokens = tokenizer.convert_ids_to_tokens(token_ids)
print(f"🧩 Tokens: {tokens}")
decoded = tokenizer.decode(token_ids)
print(f"📤 Decoded Text: {decoded}")
# 🧪 Example roundtrip test
check_tokenizer_roundtrip(
"threshold function ꯍꯥꯌꯔꯤꯕꯥ ꯅ꯭ꯌꯨꯔꯣꯅꯁꯤꯡ ꯑꯁꯤꯅꯥ ꯏꯅꯄꯨꯠꯁꯤꯡ ꯂꯧꯏ"
)
