nvidiaDiscovered 5 days ago
nvidia/parakeet-tdt-0.6b-v2
0.6B parameters · Encoder: Conformer-based · Decoder: TDT / RNN-T
0.6BAudio inputTranscription
Price not listed
Explore models.
Measured modelsSPGISpeech WER
Clear benchmark ×Ranked results
nvidiaDiscovered 5 days ago
nvidia/parakeet-tdt-0.6b-v2 (fast-gpu-asr)
0.6B parameters · Encoder: Conformer-based · Decoder: TDT
0.6BAudio inputTranscription
Price not listed
nvidiaDiscovered 5 days ago
nvidia/parakeet-tdt-0.6b-v3 (fast-gpu-asr)
0.6B parameters · 26 languages · Encoder: Conformer-based · Decoder: TDT
0.6BAudio inputTranscription
Price not listed
OpenMOSS-TeamDiscovered 5 days ago
OpenMOSS-Team/MOSS-Transcribe-Diarize
0.91B parameters · 50 languages · Encoder: Whisper audio encoder, 24 layers · Decoder: Qwen3, 28 layers
0.91BAudio inputTranscription
Price not listed
Price not listed
QwenDiscovered 5 days ago
Qwen/Qwen3-ASR-0.6B-hf
0.78B parameters · 52 languages · Encoder: Custom · Decoder: Qwen3
0.78BAudio inputTranscription
Price not listed
QwenDiscovered 5 days ago
Qwen/Qwen3-ASR-1.7B-hf
2.04B parameters · 52 languages · Encoder: Custom · Decoder: Qwen3
2.04BAudio inputTranscription
Price not listed
Price not listed
Price not listed
Price not listed
Price not listed
soundsgoodaiDiscovered 5 days ago
soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M (fast-gpu-asr, ctc_greedy_search)
0.29B parameters · Encoder: Zipformer · Decoder: CTC
0.29BAudio inputTranscription
Price not listed
soundsgoodaiDiscovered 5 days ago
soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M (fast-gpu-asr, transducer_modified_beam_search)
0.29B parameters · Encoder: Zipformer · Decoder: Transducer
0.29BAudio inputTranscription
Price not listed
Price not listed
TheStageAIDiscovered 5 days ago
TheStageAI/thewhisper-large-v3-turbo
0.8B parameters · 28 languages · Encoder: Whisper · Decoder: Transformer
0.8BAudio inputTranscription
Price not listed
Price not listed
Price not listed