Skip to content
ModelListedExternal
Download

Whisper Small Mn

Fine-tune of openai/whisper-small for Mongolian (mn) automatic speech recognition.

Sourcehuggingface.co/Blgn94/whisper-small-mn/tree/dd4f091bda687a95c732897b9370e54e3fde6023
KindText modelBase modelopenai/whisper-smallVersionBgrade

Model source

Kind
Text model
File size
922 MB
Base model
openai/whisper-small
Version
vmodel
Updated
Oct 27, 2026
Downloads
41
Source
Hugging Face

Source description

whisper-small-mn

Fine-tune of openai/whisper-small for Mongolian (mn) automatic speech recognition.

Results

Evaluated on a held-out subset of the validation split:

MetricValue
WER22.1%
CER10.3%

Training data

Trained on Blgn94/mongolian-stt-dataset (~60 h, 57,320 clips), a combination of:

  • MBSpeech (read Mongolian Bible) — MIT
  • Mozilla Common Voice 20 (mn, normalized) — CC0-1.0
  • Google FLEURS (mn) — CC-BY-4.0

All audio is 16 kHz mono.

Training procedure

  • 3 epochs, effective batch size 8 (batch 2 × grad-accum 4), fp16
  • learning rate 1e-5, 500 warmup steps
  • AdamW, gradient checkpointing

Usage

from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="Blgn94/whisper-small-mn")
text = pipe("audio.wav")["text"]
print(text)

Or with the model/processor directly:

import torch, librosa
from transformers import WhisperProcessor, WhisperForConditionalGeneration

processor = WhisperProcessor.from_pretrained("Blgn94/whisper-small-mn")
model = WhisperForConditionalGeneration.from_pretrained("Blgn94/whisper-small-mn")

audio, _ = librosa.load("audio.wav", sr=16000)
inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
ids = model.generate(inputs.input_features, language="mn", task="transcribe")
print(processor.batch_decode(ids, skip_special_tokens=True)[0])

License

CC-BY-4.0, reflecting the most restrictive license among the combined training sources.

Sources

1 source
Hugging FacePrimaryVersion dd4f091bda687a95c732897b9370e54e3fde6023
huggingface.co/Blgn94/whisper-small-mn/tree/dd4f091bda687a95c732897b9370e54e3fde6023

Verified Oct 26

Model artifacts

1 artifact

model.safetensors

safetensors · 922 MB · SHA-256 10f71bf0f2af…0bcc · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 7huggingface.co/Blgn94/whisper-small-mn

--- license: cc-by-4.0 language: - mn base_model: openai/whisper-small tags: - whisper - automatic-speech-recognition - mongolian - asr datasets: - Blgn94/mongolian-stt-dataset metrics: - wer - cer pipeline_tag: automatic-speech-recognition model-index: - name: whisper-small-mn results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Blgn94/mongolian-stt-dataset type: Blgn94/mongolian-stt-dataset metrics: - type: wer value: 22.12 name: WER - type: cer value: 10.29 name: CER --- # whisper-small-mn Fine-tune of [`openai/whisper-small`](https://huggingface.co/openai/whisper-small) for **Mongolian (mn)** automatic speech recognition. ## Results Evaluated on a held-out subset of the validation split: | Metric | Value | |--------|-------| | WER | 22.1% | | CER | 10.3% | ## Training data Trained on [`Blgn94/mongolian-stt-dataset`](https://huggingface.co/datasets/Blgn94/mongolian-stt-dataset) (~60 h, 57,320 clips), a combination of: - **MBSpeech** (read Mongolian Bible) — MIT - **Mozilla Common Voice 20** (mn, normalized) — CC0-1.0 - **Google FLEURS** (mn) — CC-BY-4.0 All audio is 16 kHz mono. ## Training procedure - 3 epochs, effective batch size 8 (batch 2 × grad-accum 4), fp16 - learning rate 1e-5, 500 warmup steps - AdamW, gradient checkpointing ## Usage ```python from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Blgn94/whisper-small-mn") text = pipe("audio.wav")["text"] print(text) ``` Or with the model/processor directly: ```python import torch, librosa from transformers import WhisperProcessor, WhisperForConditionalGeneration processor = WhisperProcessor.from_pretrained("Blgn94/whisper-small-mn") model = WhisperForConditionalGeneration.from_pretrained("Blgn94/whisper-small-mn") audio, _ = librosa.load("audio.wav", sr=16000) inputs = processor(audio, sampling_rate=16000, return_tensors="pt") ids = model.generate(inputs.input_features, language="mn", task="transcribe") print(processor.batch_decode(ids, skip_special_tokens=True)[0]) ``` ## License CC-BY-4.0, reflecting the most restrictive license among the combined training sources.

NoteOct 26huggingface.co/Blgn94/whisper-small-mn

Source context: 41 downloads · 0 likes · Pipeline automatic-speech-recognition · Repo Blgn94/whisper-small-mn

NoteAug 7huggingface.co/Blgn94/whisper-small-mn

Source context: 178 downloads · 0 likes · Pipeline automatic-speech-recognition · Repo Blgn94/whisper-small-mn