diaslmb's picture
Update README.md
1adf249 verified
metadata
license: apache-2.0
language:
  - kk
base_model:
  - microsoft/VibeVoice-ASR
tags:
  - automatic-speech-recognition
  - kazakh
  - vibevoice
  - lora
  - ksc2
datasets:
  - InflexionLab/ISSAI-KSC2-Structured
metrics: null
model-index:
  - name: VibeVoice-ASR-Kazakh
    results:
      - task:
          type: ASR
        dataset:
          type: AudioDataset
          name: ISSAI KSC2
        metrics:
          - type: WER
            value: 22%

VibeVoice ASR — Kazakh

Model Description

This is VibeVoice ASR fine-tuned on the Kazakh language using the ISSAI KSC2 Structured dataset (~1,200 hours of diverse Kazakh speech). Fine-tuning was performed using LoRA (Low-Rank Adaptation) and the weights were merged into the base model for efficient inference. Model demonstrated 22% WER on test set of ISSAI KSC2.

The base VibeVoice ASR model had no prior Kazakh knowledge. This fine-tuned version produces punctuated and capitalized Kazakh transcriptions.

Training Dataset

InflexionLab/ISSAI-KSC2-Structured — an enhanced version of the ISSAI KSC2 corpus with punctuation and capitalization restored using Gemma 27B. Covers 6 domains: TV News, Crowdsourced, Parliament, Talkshow, Podcasts, and Radio.

Evaluation Results

Evaluated on the KSC2 Test split (9,351 samples) and farabi-lab/kazakh-stt 30K samples. Farabi-Lab dataset was not included in training.

Dataset WER (Fine-tuned) CER (Fine-tuned)
ISSAI_KSC2 ~22% ~9.6%
farabi-lab/kazakh-stt 17.6% 4.25%