GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Ken-Z
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
Ken-Z
Model Tree
openai/whisper-large-v3-turbo
Input Modalities
Output Modalities
Supported Functionality
Test set: 2,060 clips from speakers who do not appear in training
(5.6 h). Decoding: beam size 5, language="latin".
Before scoring, both reference and prediction are normalized: diacritics
(macrons) stripped, lowercased, v→u, j→i, digits and punctuation removed.
| Model | WER % | CER % |
|---|---|---|
| latin_whisper-large-v3-turbo (this model) | 13.01 | 2.74 |
openai/whisper-large-v3-turbo (no fine-tuning) | 35.55 | 8.03 |
Splits (splits.json) are included in this repository.
python
from transformers import pipelineasr = pipeline("automatic-speech-recognition", model="Ken-Z/latin_whisper-large-v3-turbo")print(asr("clip.wav", generate_kwargs={"language": "latin", "task": "transcribe"})["text"])For audio longer than 30 seconds, add chunk_length_s=30 to the asr(...) call.
Output is lowercase Latin without macrons or punctuation, written with u and i (no v or j).
openai/whisper-large-v3-turboVox Classica (CC-BY-4.0)