Views
No views yet
nvidia/parakeet-tdt-0.6b-v3 for Apple Silicon (ANE).
Derived from FluidInference/parakeet-tdt-0.6b-v3-coreml,
with an additional JointSingleStep.mlmodelc that exposes raw token + duration
logits per step.JointSingleStep lets host-side code (e.g. FluidAudio's
ParakeetBooster) add log-prob offsets to the token logits before argmax —
the shallow-fusion step needed for trie-based context/vocabulary biasing.
The standard JointDecision.mlmodelc argmaxes inside the CoreML graph and
can't be biased.| File | Purpose |
|---|---|
Preprocessor.mlmodelc | Log-mel frontend, 15 s window, 16 kHz mono |
Encoder.mlmodelc | FastConformer encoder |
Decoder.mlmodelc | RNN-T prediction network (LSTM, U=1 streaming) |
JointDecision.mlmodelc | Single-step joint + argmax (token_id, prob, duration) |
JointSingleStep.mlmodelc | Single-step joint — raw token_logits + duration_logits (for biasing) |
parakeet_vocab.json / parakeet_v3_vocab.json | SentencePiece vocabulary |
config.json | Metadata |
boosting), which downloads this bundle by default for
AsrModelVersion.v3. See
Sources/FluidAudio/ASR/Parakeet/SlidingWindow/CustomVocabulary/Boosting/
for ParakeetBooster / TokenBoostTrie.JointSingleStep was generated with the script at
mobius/models/stt/parakeet-tdt-v3-0.6b/coreml.
The wrapper adds a JointSingleStep class that returns token_logits and
duration_logits directly.