GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Ogaal-Labs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Ogaal-Labs
Model Tree
openai/whisper-large-v3
Input Modalities
Output Modalities
Supported Functionality
0.21660.10540.22780.1186openai/whisper-large-v3WhisperForConditionalGeneration39,60442942872.1 hours60.0001so)A private Ogaal Labs collection contributed roughly 5,000 curated prompts recorded by 19 speakers across varied genders, accents, and speaking styles. English was not part of the training objective.
python
from transformers import pipelinepipe = pipeline("automatic-speech-recognition",model="Ogaal-Labs/Ogaal-ASR",)result = pipe("test.wav")print(result["text"])
Use the companion GitHub repository for local CPU/GPU inference and the browser demo:
bash
git clone https://github.com/Ogaal-Labs/Ogaal-ASR.gitcd Ogaal-ASRpython -m venv .venvsource .venv/bin/activatepip install -r requirements.txtgit clone https://huggingface.co/Ogaal-Labs/Ogaal-ASR modelpython scripts/infer_somali_asr.py \--audio-path /path/to/audio.wav \--model-dir model
Requirements: Python 3.10 or newer and ffmpeg on the system path.
model.safetensors: fine-tuned Whisper weightsconfig.json, generation_config.json, processor_config.json: runtime configurationtokenizer.json, tokenizer_config.json: tokenizer assetsbest_val_metrics.json, test_metrics.json: held-out evaluation summariesTECHNICAL_BOOK.md, MODEL_SCOPE.md: supporting release documentationTECHNICAL_BOOK.mdMODEL_SCOPE.mdThis model repository is released under the Apache License 2.0. The base openai/whisper-large-v3 model is also distributed under Apache-2.0.