Modelpublic

computeram/badini-w2v-bert-normalized

sourceHugging Facemitupdated 3d agoView on Hugging Face

0likes37downloads

Model Card

Badini Kurdish ASR — Normalized (Wav2Vec2-BERT)

An automatic speech recognition (ASR) model for Badini Kurdish (a variety of Kurmanji, written in Arabic script), fine-tuned from `facebook/w2v-bert-2.0` with a CTC head.

This repository includes a companion text-normalization module (badini_normalize.py) alongside the model. Following the usage example below applies punctuation handling, number expansion, and character normalization to the raw model output.

Input requirements

—Audio must be 16 kHz, mono.
—Resample any other sample rate to 16 kHz before inference.

Usage

python

import torch, soundfile as sf
from transformers import Wav2Vec2BertForCTC, Wav2Vec2BertProcessor
from huggingface_hub import hf_hub_download
import importlib.util

repo_id = "computeram/badini-w2v-bert-normalized"

# download and load the companion normalization module
norm_path = hf_hub_download(repo_id, "badini_normalize.py")
spec = importlib.util.spec_from_file_location("badini_normalize", norm_path)
badini_normalize = importlib.util.module_from_spec(spec)
spec.loader.exec_module(badini_normalize)

processor = Wav2Vec2BertProcessor.from_pretrained(repo_id)
model = Wav2Vec2BertForCTC.from_pretrained(repo_id).eval()

speech, sr = sf.read("audio.wav")   # 16 kHz mono
inputs = processor(speech, sampling_rate=16000, return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits
pred_ids = torch.argmax(logits, dim=-1)
raw_text = processor.batch_decode(pred_ids)[0]

# apply the normalization pipeline (punctuation handling, Badini number
# expansion, character/word-variant unification)
text = badini_normalize.normalize_transcript(raw_text)
print(text)

Intended use

Speech transcription for Badini Kurdish, with the recommended normalization already applied by following the usage example above.