whisper-tiny-kat-32768

This model is a 19.42% smaller version of openai/whisper-tiny optimized for Georgian language via vocabulary size reduction using the trimming method.
This trimmed model should perform similarly to the original model with only 32,768 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.

Model Statistics

Metric Original Trimmed Reduction
Vocabulary size 51,865 tokens 32,768 tokens 36.82%
Model size 37,760,640 params 30,427,392 params 19.42%

image

Mining Dataset Statistics

Usage

from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
import librosa

# Pipeline function
processor = AutoProcessor.from_pretrained("alphaedge-ai/whisper-tiny-kat-32768")
pipe = pipeline(
    "automatic-speech-recognition",
    model="alphaedge-ai/whisper-tiny-kat-32768",
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    generate_kwargs={"language": "georgian", "task": "transcribe"},
)

# Loading and resampling at 16 kHz (required by Whisper)
audio_array, sampling_rate = librosa.load(audio_path, sr=16000)

# Result
result = pipe(audio_array)
print("Transcription :", result["text"])

Citations

Whisper

@misc{radford2022whisper,
  doi = {10.48550/ARXIV.2212.04356},
  url = {https://arxiv.org/abs/2212.04356},
  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

Trimming blog post

@misc{hf_blogpost_trimming,
      title={Introduction to Trimming}, 
      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
      year={2026},
      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
}
Downloads last month
9
Safetensors
Model size
30.4M params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for alphaedge-ai/whisper-tiny-kat-32768

Quantized
(224)
this model

Dataset used to train alphaedge-ai/whisper-tiny-kat-32768

Collection including alphaedge-ai/whisper-tiny-kat-32768

Paper for alphaedge-ai/whisper-tiny-kat-32768