GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Zilai2999
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Zilai2999
Model Tree
openai/whisper-medium.en
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import pipeline asr = pipeline( "automatic-speech-recognition", model="Zilai2999/whisper-medium.en-gumbel-beard",)print(asr("audio.wav")["text"])Or with the model/processor directly:
python
import torch, librosafrom transformers import WhisperForConditionalGeneration, WhisperProcessor model_id = "Zilai2999/whisper-medium.en-gumbel-beard"processor = WhisperProcessor.from_pretrained(model_id)model = WhisperForConditionalGeneration.from_pretrained(model_id) audio, _ = librosa.load("audio.wav", sr=16000)inputs = processor(audio, sampling_rate=16000, return_tensors="pt")ids = model.generate(inputs.input_features)print(processor.batch_decode(ids, skip_special_tokens=True)[0])Audio is expected at 16 kHz.
See the code repository for the full recipe and hyper-parameters.
| Test set | WER |
|---|---|
| MyST | 8.2% |
bibtex
@inproceedings{gumbelbeard2026, title = {Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains}, booktitle = {Proc. Interspeech}, year = {2026},}import torch, librosafrom transformers import WhisperForConditionalGeneration, WhisperProcessor model_id = "Zilai2999/whisper-medium.en-gumbel-beard"processor = WhisperProcessor.from_pretrained(model_id)model = WhisperForConditionalGeneration.from_pretrained(model_id) audio, _ = librosa.load("audio.wav", sr=16000)inputs = processor(audio, sampling_rate=16000, return_tensors="pt")ids = model.generate(inputs.input_features)print(processor.batch_decode(ids, skip_special_tokens=True)[0])@inproceedings{gumbelbeard2026, title = {Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains}, booktitle = {Proc. Interspeech}, year = {2026},}