Model reference · open weights

higgs-audio-stt

Available as managed deployment Audio bosonai Speech→text 2 variants 19k dl/mo

higgs-audio-stt is an open-weight audio or speech model from bosonai. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bybosonai
TypeAudio & music
TaskSpeech→text
Parameters (lead)8.9B
Context32k tokens
Based onbosonai/higgs-audio-v3-8b
Released2026-04-27
Popularity19k downloads / month
LicenceOpen weights

About

What higgs-audio-stt is

A speech-to-text model combining a Whisper-Large-v3 encoder with a Qwen3-8B decoder (8.91B total parameters), fine-tuned with LoRA on diverse ASR benchmarks.

Read the full model card

Usage

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

# Load model
model = AutoModel.from_pretrained(
    "bosonai/higgs-audio-v3-8b-stt-v2",
    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-v2")

# 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-v2", "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)

Requirements

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

Architecture

  • Encoder: Whisper-Large-v3 (frozen)
  • Decoder: Qwen3-8B (LoRA fine-tuned, merged)
  • Total parameters: 8.91B
  • Audio input: 16kHz mono WAV
  • Supports: Thinking mode for improved accuracy

Performance (ESB Benchmark — Full Scale, All Samples)

DatasetWER
AMI10.14%
Earnings228.73%
GigaSpeech8.47%
LibriSpeech Clean1.25%
LibriSpeech Other2.38%
SPGISpeech3.60%
TED-LIUM3.09%
VoxPopuli5.92%
Average5.449%

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Automatic Speech RecognitionAMI (Meetings test)Test WER10.140
Automatic Speech RecognitionEarnings-22Test WER8.730
Automatic Speech RecognitionGigaSpeechTest WER8.470
Automatic Speech RecognitionLibriSpeech (clean)Test WER1.250
Automatic Speech RecognitionLibriSpeech (other)Test WER2.380
Automatic Speech RecognitionSPGI SpeechTest WER3.600
Automatic Speech Recognitiontedlium-v3Test WER3.090
Automatic Speech RecognitionVox PopuliTest WER5.920

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys higgs-audio-stt for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (higgs-audio-stt below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="higgs-audio-stt" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms