bosonai/higgs-audio-v3-8b-stt

import torch
import numpy as np
from transformers import AutoModel, AutoTokenizer

# Load model
model = AutoModel.from_pretrained(
    "bosonai/higgs-audio-v3-8b-stt",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    attn_implementation="eager",
    device_map="cuda:0",
)
tokenizer = AutoTokenizer.from_pretrained("bosonai/higgs-audio-v3-8b-stt")

# Transcribe audio (16kHz mono numpy array)
from transformers.utils import cached_file
import importlib.util
spec = importlib.util.spec_from_file_location("transcribe", cached_file("bosonai/higgs-audio-v3-8b-stt", "transcribe.py", _raise_exceptions_for_connection_errors=False))
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)

audio_np = np.random.randn(16000).astype(np.float32)  # replace with your audio
text = mod.transcribe(model, tokenizer, audio_np)
print(text)

torch
transformers>=4.51.0
whisper  # for audio preprocessing (WhisperProcessor)