bosonai/higgs-audio-v3-stt
2.68B parameters · 1 language · Encoder: Whisper · Decoder: Qwen3
Measured modelsVoice Arena Monsoon WER
Clear benchmark ×Choose a category in More filters to see relevant price sorts.
2.68B parameters · 1 language · Encoder: Whisper · Decoder: Qwen3
1.15B parameters · 19 languages · Encoder: Whisper · Decoder: Qwen2
3.75B parameters · 19 languages · Encoder: Whisper · Decoder: Qwen2
0.324B parameters · 7 languages · Encoder: Qwen3-ASR audio encoder · Decoder: 8-layer Qwen-style causal LM
0.83B parameters · 4 languages · Encoder: Qwen3-ASR · Decoder: Custom
5.18B parameters · 2 languages · Encoder: Qwen3-Omni encoder · Decoder: Qwen3-4B
8B parameters · 50 languages · Encoder: Custom · Decoder: Qwen2
2.5B parameters · Encoder: Conformer-based · Decoder: Qwen2
0.91B parameters · 50 languages · Encoder: Whisper audio encoder, 24 layers · Decoder: Qwen3, 28 layers
0.78B parameters · 52 languages · Encoder: Custom · Decoder: Qwen3
2.04B parameters · 52 languages · Encoder: Custom · Decoder: Qwen3