GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
shehzadkhalid04
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
shehzadkhalid04
Model Tree
Base
openai/whisper-medium
Adapter
this model
Input Modalities
Audio
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
openai/whisper-medium
Balochi Arabic script.
openai/whisper-mediumBalochi is not a built-in Whisper language token. Do not force English or translation.
python
model.config.forced_decoder_ids = Nonemodel.generation_config.forced_decoder_ids = None
python
import torchfrom transformers import WhisperForConditionalGeneration, WhisperProcessorfrom peft import PeftModelbase_model_id = "openai/whisper-medium"adapter_id = "shehzadkhalid04/balochi-whisper-medium"device = "cuda" if torch.cuda.is_available() else "cpu"dtype = torch.float16 if torch.cuda.is_available() else torch.float32processor = WhisperProcessor.from_pretrained(adapter_id, subfolder="processor")base_model = WhisperForConditionalGeneration.from_pretrained(base_model_id,torch_dtype=dtype,low_cpu_mem_usage=True,use_safetensors=True,).to(device)model = PeftModel.from_pretrained(base_model, adapter_id).to(device)model.eval()model.config.forced_decoder_ids = Nonemodel.generation_config.forced_decoder_ids = None