Inconsistent model documentation around streaming support

[abb128]

Nemotron

https://huggingface.co/handy-computer/nemotron-speech-streaming-en-0.6b-gguf

Offline English speech-to-text with punctuation and capitalization
transcribe.cpp does not yet expose a streaming session API

This contradicts documentation within the repo

https://github.com/handy-computer/transcribe.cpp/blob/main/docs/models/nemotron-speech-streaming-en-0.6b.md

This port runs the model in both offline and cache-aware streaming modes

Parakeet

https://huggingface.co/handy-computer/parakeet-unified-en-0.6b-gguf

Offline English speech-to-text with punctuation and capitalization. A 0.6B-parameter FastConformer encoder with an RNN-T transducer decoder, trained as a 'unified' streaming/offline model. This port runs the model in offline mode only — streaming attention contexts are present in the GGUF but transcribe.cpp does not yet expose a streaming entry.

https://github.com/handy-computer/transcribe.cpp/blob/main/docs/models/parakeet.md

Streaming / real-time → Nemotron streaming. Parakeet here is offline-only.

However, looking at the actual code, there appears to be streaming code for Parakeet

transcribe.cpp/src/arch/parakeet/model.cpp

Line 2836 in e2f82cb

// -------- Buffered streaming path (parakeet-unified-en-0.6b) --------

Moonshine

https://huggingface.co/handy-computer/moonshine-streaming-tiny-gguf

Offline English speech-to-text. A 34M-parameter encoder-decoder ASR model designed for streaming use

The word "Offline" probably doesn't fit here because in ASR it means the opposite of streaming. This word is included on all different Moonshine Streaming sizes