GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
G999n
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
G999n
Model Tree
openai/whisper-large-v3-turbo
Input Modalities
Output Modalities
Supported Functionality
openai/whisper-large-v3-turboor / proxy script guidance bengali)ai4bharat/IndicVoices (Odia split)64128q_proj, v_proj11.8M / 809M (1.46%)python
import torchimport librosafrom transformers import WhisperProcessor, WhisperForConditionalGenerationfrom peft import PeftModel base_model_id = "openai/whisper-large-v3-turbo"peft_model_id = "G999n/whisper-large-v3-turbo-odia-lora" # 1. Load processor & base modelprocessor = WhisperProcessor.from_pretrained(base_model_id, language="bengali", task="transcribe")model = WhisperForConditionalGeneration.from_pretrained(base_model_id, torch_dtype=torch.float16, device_map="auto") # 2. Attach LoRA adaptermodel = PeftModel.from_pretrained(model, peft_model_id)model.eval() # 3. Transcribe audioaudio, sr = librosa.load("your_odia_audio.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to("cuda", dtype=torch.float16) with torch.no_grad(): predicted_ids = model.generate(input_features, max_length=225) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]print("Transcribed Odia Text:", transcription)Trained on Google Cloud Platform using an NVIDIA L4 GPU.
import torchimport librosafrom transformers import WhisperProcessor, WhisperForConditionalGenerationfrom peft import PeftModel base_model_id = "openai/whisper-large-v3-turbo"peft_model_id = "G999n/whisper-large-v3-turbo-odia-lora" # 1. Load processor & base modelprocessor = WhisperProcessor.from_pretrained(base_model_id, language="bengali", task="transcribe")model = WhisperForConditionalGeneration.from_pretrained(base_model_id, torch_dtype=torch.float16, device_map="auto") # 2. Attach LoRA adaptermodel = PeftModel.from_pretrained(model, peft_model_id)model.eval() # 3. Transcribe audioaudio, sr = librosa.load("your_odia_audio.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to("cuda", dtype=torch.float16) with torch.no_grad(): predicted_ids = model.generate(input_features, max_length=225) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]print("Transcribed Odia Text:", transcription)