GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
vk496
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
vk496
Model Tree
Ari/whisper-small-es
Input Modalities
Output Modalities
Supported Functionality
python
import numpy as npfrom pydub import AudioSegmentfrom transformers import WhisperForConditionalGeneration, WhisperProcessor processor = WhisperProcessor.from_pretrained("whisper-small-esl")model = WhisperForConditionalGeneration.from_pretrained("whisper-small-esl") audio = AudioSegment.from_file("audio.mp3").set_frame_rate(16000).set_channels(1)samples = np.frombuffer(audio.raw_data, np.int16).astype(np.float32) / 32768.0features = processor(samples, sampling_rate=16000, return_tensors="pt").input_featurestext = processor.batch_decode(model.generate(features), skip_special_tokens=True)[0]print(text)