kazakh-whisper-large-v3-turbo

Key Features

• Optimized specifically for Kazakh ASR
• Trained on 841k+ speech-transcript pairs
• 1,500+ hours of speech
• Based on Whisper Large-v3 Turbo
• Ready-to-use Transformers checkpoint
• Evaluated on external and internal benchmarks
• Compatible with Hugging Face pipelines
• Suitable for production and research use

---

Benchmark Summary

FLEURS Kazakh Test

The model achieves the strongest performance among the evaluated open-source Kazakh ASR systems in this benchmark suite.

Internal Kazakh ASR Test Set

This benchmark uses a fixed 5,000-example held-out test subset from the cleaned Kazakh ASR mixture.

This evaluation is an internal benchmark and should be interpreted as a secondary result. The FLEURS Kazakh test is used as the main external benchmark.

---

Inference Speed Benchmark

Inference speed was measured on 106 audio files (30.27 minutes total audio) using a Kaggle NVIDIA T4 GPU.

This benchmark is intended to provide a practical comparison of recognition speed across commonly used open-source ASR models.

Notes

• WER (Word Error Rate): lower is better.
• CER (Character Error Rate): lower is better.
• RTF (Real-Time Factor): lower is faster.
• Speed: audio duration divided by inference time. Higher is faster.

While the Wav2Vec2 baseline provides the fastest inference speed, Kazakh Whisper Large-v3 Turbo achieves substantially stronger recognition quality while maintaining practical real-time performance.

Among the evaluated models, Kazakh Whisper Large-v3 Turbo provides the best overall quality-speed tradeoff for Kazakh speech recognition workloads.

---

Usage

Installation

bash
Copy code
pip install transformers accelerate torch torchaudio

Quick Start

The model can be used directly with the Hugging Face pipeline() API:

python
Copy code
from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="shyngys879/kazakh-whisper-large-v3-turbo"
)

result = asr(
    "audio.wav",
    generate_kwargs={
        "language": "kk",
        "task": "transcribe"
    }
)

print(result["text"])

GPU Inference

For faster inference, use GPU inference with FP16:

python
Copy code
import torch
from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="shyngys879/kazakh-whisper-large-v3-turbo",
    torch_dtype=torch.float16,
    device="cuda"
)

result = asr(
    "audio.wav",
    generate_kwargs={
        "language": "kk",
        "task": "transcribe"
    }
)

print(result["text"])

CPU Inference

python
Copy code
from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="shyngys879/kazakh-whisper-large-v3-turbo",
    device="cpu"
)

result = asr(
    "audio.wav",
    generate_kwargs={
        "language": "kk",
        "task": "transcribe"
    }
)

print(result["text"])

Long Audio

For long audio files such as meetings, podcasts, interviews, and lectures, use chunked inference:

python
Copy code
from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="shyngys879/kazakh-whisper-large-v3-turbo",
    chunk_length_s=30,
    batch_size=8
)

result = asr(
    "meeting.wav",
    generate_kwargs={
        "language": "kk",
        "task": "transcribe"
    }
)

print(result["text"])

Batch Processing

python
Copy code
from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="shyngys879/kazakh-whisper-large-v3-turbo"
)

files = [
    "audio1.wav",
    "audio2.wav",
    "audio3.wav"
]

for file in files:
    result = asr(
        file,
        generate_kwargs={
            "language": "kk",
            "task": "transcribe"
        }
    )

    print(file, result["text"])

Direct Transformers Usage

The model can also be used directly with WhisperProcessor and WhisperForConditionalGeneration:

python
Copy code
import torch
import torchaudio
from transformers import WhisperProcessor, WhisperForConditionalGeneration

model_id = "shyngys879/kazakh-whisper-large-v3-turbo"

processor = WhisperProcessor.from_pretrained(model_id)

model = WhisperForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

audio_path = "audio.wav"

speech_array, sampling_rate = torchaudio.load(audio_path)

if sampling_rate != 16000:
    resampler = torchaudio.transforms.Resample(sampling_rate, 16000)
    speech_array = resampler(speech_array)

audio_array = speech_array.squeeze().numpy()

inputs = processor(
    audio_array,
    sampling_rate=16000,
    return_tensors="pt"
)

input_features = inputs.input_features.to(
    model.device,
    dtype=torch.float16
)

with torch.no_grad():
    predicted_ids = model.generate(
        input_features,
        language="kk",
        task="transcribe",
        max_new_tokens=225
    )

text = processor.batch_decode(
    predicted_ids,
    skip_special_tokens=True
)[0]

print("Prediction:", text)

Dataset Annotation

python
Copy code
from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="shyngys879/kazakh-whisper-large-v3-turbo"
)

audio_files = [
    "sample1.wav",
    "sample2.wav",
    "sample3.wav"
]

annotations = []

for audio_file in audio_files:
    result = asr(
        audio_file,
        generate_kwargs={
            "language": "kk",
            "task": "transcribe"
        }
    )

    annotations.append({
        "audio": audio_file,
        "transcript": result["text"]
    })

print(annotations)

Best Practices

For best performance:

• Use 16 kHz audio when possible.
• Use language="kk" and task="transcribe".
• Segment very long recordings before transcription.
• Use chunked inference for meetings, podcasts, interviews, and lectures.
• Use GPU inference for large-scale workloads.
• Use clean speech recordings whenever possible.

---

Training Data

The model was trained on a cleaned and deduplicated mixture of public Kazakh ASR datasets:

• issai/Kazakh_Speech_Corpus_2
• farabi-lab/kazakh-stt
• voice-biomarkers/openslr-140-hq-Kazakh
• Flamme-VRM/kazakh-speech-dataset
• SRP-base-model-training/kazakh_speech_dataset_ksd
• Shirali/ISSAI_KSC_335RS_v_1_1
• SRP-base-model-training/kazakh_speech_corpus_2
• sarulab-speech/yodas2_sidon

Dataset Statistics

---

Intended Applications

This model can be used for:

• Speech transcription
• Subtitle generation
• Podcast transcription
• Interview transcription
• Meeting transcription
• Voice assistants
• Dataset annotation
• Educational applications
• Call-center analytics
• Kazakh NLP pipelines

---

Model Details

---

Limitations

Performance may degrade on:

• Heavy background noise
• Overlapping speakers
• Strong accents or dialects
• Code-switched Kazakh/Russian speech
• Music-heavy recordings
• Very long audio without segmentation

---

Citation

bibtex
Copy code
@misc{sovetkhan2026kazakhwhisper,
  title={Kazakh Whisper Large-v3 Turbo},
  author={Shyngys Sovetkhan},
  year={2026},
  howpublished={Hugging Face Model Hub},
  url={https://huggingface.co/shyngys879/kazakh-whisper-large-v3-turbo}
}