GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
amedcj
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
amedcj
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Trained on Common Voice Kurmanji.
python
from transformers import WhisperProcessor, WhisperForConditionalGenerationimport torchimport torchaudio processor = WhisperProcessor.from_pretrained("amedcj/whisper-kurmanji")model = WhisperForConditionalGeneration.from_pretrained("amedcj/whisper-kurmanji").to("cuda") audio, sr = torchaudio.load("your_audio.wav")input_features = processor(audio.squeeze(), sampling_rate=16000, return_tensors="pt").input_features.to("cuda")forced_decoder_ids = processor.get_decoder_prompt_ids(language="kurmanji", task="transcribe") predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]print(transcription)