No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from moondream/parakeet-ultra
All models by moondream →A post-trained version of parakeet-tdt-0.6b-v3. Same architecture, same tokenizer, same 0.6B parameters in full precision. It is better than the original on every benchmark group below, by a wide margin on the 25-language FLEURS set, in background noise and on long-form audio, and it runs faster than the original does in NeMo.
Its sibling Parakeet Redux is the ternary version of the same architecture, 178 MB, built for CPUs and Apple silicon. Read the release post for the story behind both models.
Run it with Photon. Every accuracy number on this page is Photon on an NVIDIA GPU.
Real-time factor: seconds of audio transcribed per second of wall clock, higher is faster. One NVIDIA B200, 128 requests in flight, the same files on both sides; NeMo 3.0 runs the original checkpoint with its own transcribe call at batch 128, Photon runs parakeet-ultra.
Word error rate in percent, lower is better. Both models are scored on the same files with the Open ASR Leaderboard's own pipeline as of September 2026 (its normalizers and compound-merging alignment, with the FLEURS references prepared as the leaderboard's text column is). parakeet-ultra runs in Photon on an NVIDIA GPU, the original in NeMo in bf16.
The seven English test sets of the Hugging Face Open ASR Leaderboard: audiobooks (LibriSpeech), meetings (AMI), earnings calls (Earnings-22), podcasts and YouTube (GigaSpeech), financial calls (SPGISpeech) and parliament (VoxPopuli).
The FLEURS test split: read Wikipedia sentences, a few hundred per language, for all 25 languages the model supports.
The AMI and VoxPopuli test sets with the Artificial Analysis cleaning applied, and Earnings-22 scored in 30-second chunks joined per call, the way the AA-WER benchmark does it.
The clean sets with MUSAN noise (the half of the corpus not used for training) mixed in at a fixed signal-to-noise ratio; 0 dB means the noise is as loud as the speech.
Eleven complete TED-LIUM 3 talks of 10-20 minutes each. parakeet-ultra transcribes them through Photon, whose segmenter cuts each talk at pauses found by the model's VAD head into segments of at most 30 seconds; the original runs NeMo's own long-audio path.
# pip install moondreamimport moondream as md
with md.photon("moondream/parakeet-ultra") as speech: result = speech.transcribe(audio="speech.wav") print(result["text"])
# timestamps="segment": one entry per sentence, with its start # and end in seconds; "word" adds the start and end of every word result = speech.transcribe(audio="speech.wav", timestamps="word") for segment in result["segments"]: print(segment["start"], segment["end"], segment["text"]) for word in segment["words"]: print(word["start"], word["end"], word["word"])