Explore models.
google/gemma-4-12B-it
140 languages · Decoder: Transformer
google/gemma-4-E2B-it
140 languages · Encoder: Conformer · Decoder: Transformer
google/gemma-4-E4B-it
7.94B parameters · 140 languages · Encoder: Conformer · Decoder: Transformer
HojoAI/Hojo-ASR-V1
5.18B parameters · 2 languages · Encoder: Qwen3-Omni encoder · Decoder: Qwen3-4B
ibm-granite/granite-4.0-1b-speech
2B parameters · 6 languages · Encoder: Conformer-based · Decoder: Granite
ibm-granite/granite-speech-3.3-2b
3B parameters · 5 languages · Encoder: Conformer-based · Decoder: Granite
ibm-granite/granite-speech-3.3-8b
9B parameters · 5 languages · Encoder: Conformer-based · Decoder: Granite
ibm-granite/granite-speech-4.1-2b
2B parameters · 6 languages · Encoder: Conformer-based · Decoder: Granite
ibm-granite/granite-speech-4.1-2b-nar
2B parameters · 5 languages · Encoder: Conformer-based · Decoder: Hybrid CTC-LLM
ibm-granite/granite-speech-5.0-470m-turboctc
0.47B parameters · Encoder: Streaming-style Conformer · Decoder: CTC
ibm-granite/granite-speech-5.0-470m-turboctc-nc
0.47B parameters · Encoder: Streaming-style Conformer · Decoder: CTC
microsoft/azure-speech-06-2026
25 languages · Decoder: LLM
microsoft/azure-speech-07-2026
25 languages · Decoder: LLM
microsoft/Phi-4-multimodal-instruct
6B parameters · 8 languages · Encoder: Conformer-based · Decoder: Phi-4-Mini-Instruct
microsoft/VibeVoice-ASR-HF
8B parameters · 50 languages · Encoder: Custom · Decoder: Qwen2
mistralai/Voxtral-Mini-4B-Realtime-2602
4B parameters · 13 languages · Encoder: Custom · Decoder: Transformer
nvidia/canary-1b-v2
1B parameters · 25 languages · Encoder: Conformer-based · Decoder: Transformer
nvidia/canary-qwen-2.5b
2.5B parameters · Encoder: Conformer-based · Decoder: Qwen2
nvidia/nemotron-3.5-asr-streaming-0.6b
0.64B parameters · 40 languages · Encoder: FastConformer (cache-aware) · Decoder: RNNT
nvidia/nemotron-speech-streaming-en-0.6b
0.62B parameters · Encoder: FastConformer (cache-aware) · Decoder: RNNT
nvidia/parakeet-ctc-1.1b
1.1B parameters · Encoder: Conformer-based · Decoder: CTC