| --- |
| language: |
| - kmr |
| license: mit |
| library_name: transformers |
| tags: |
| - automatic-speech-recognition |
| - wav2vec2-bert |
| - kurdish |
| - badini |
| - kurmanji |
| - low-resource |
| base_model: facebook/w2v-bert-2.0 |
| pipeline_tag: automatic-speech-recognition |
| --- |
| |
| # Badini Kurdish ASR (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`](https://huggingface.co/facebook/w2v-bert-2.0) |
| with a CTC head. |
|
|
|
|
| ## Input requirements |
|
|
| - Audio must be **16 kHz, mono**. |
| - Resample any other sample rate to 16 kHz before running inference. |
|
|
| ## Usage |
|
|
| ```python |
| import torch, soundfile as sf |
| from transformers import Wav2Vec2BertForCTC, Wav2Vec2BertProcessor |
| |
| repo_id = "computeram/badini-w2v-bert" |
| 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) |
| print(processor.batch_decode(pred_ids)[0]) |
| ``` |
|
|
| ## Important: text normalization |
|
|
| This repository contains **only the acoustic model**. The raw output is plain CTC |
| decoding. A separate normalization pipeline — punctuation restoration, |
| number-to-word expansion (with Badini-specific remapping), character |
| normalization, and word-variant correction — is applied in the downstream |
| application and is **not** included here. Output straight from this model will |
| not match the fully normalized transcripts. |
|
|
| ## Intended use |
|
|
| Speech transcription for Badini Kurdish. Given the WER, best used with |
| downstream normalization/post-processing rather than as raw final text. |
|
|
