Docs / Reference
Changelog
Recent changes to the public fermion package, verified against the shipped package source.
0.1.24
- Fixes a startup failure on systems with a broken torchaudio install; the runtime now starts and tells you how to remove the broken package.
- Requirements: on Linux x86-64 the CPU speech engine needs glibc 2.34 or newer (Ubuntu 22.04, Debian 12, RHEL 9 and later) and about 7 GB of free RAM. macOS and Windows requirements are unchanged.
0.1.23
- Long recordings are transcribed in full.
fermion transcribeandPOST /v1/audio/transcriptionsdecoded a whole file in one pass with a token budget sized for a single utterance, so anything over about two minutes came back truncated and anything over about three degenerated into a repeated letter. Audio longer than 35 s is now cut into 25 to 35 s windows at pauses and each window is decoded on its own, on both the MLX and the CPU engine. Audio up to 35 s takes the unchanged single-pass path, so short-utterance transcripts are byte-identical to 0.1.22. --jsonaddswall_secondsnext to the decode-onlydecode_seconds, per-segment start and end times,segment_count, andtruncated.--verboseprints the same, labelled.verbose_jsonon the server fillssegmentsand reportstruncated.- One always-on line at engine start names the decode backend (mlx or cpu) and the model, and says on the first run in a new environment that the run compiles once and later runs are fast.
- A Python running under Rosetta on an Apple-silicon Mac is told so, with the fix (an arm64 Python), instead of being refused as an Intel Mac.
0.1.22
- The CPU speech engine now also runs on ARM Linux (aarch64):
fermion transcribeand a speechfermion servework on 64-bit ARM Linux machines with the same install line as x86-64 Linux. The models are the same verified downloads, and transcription stays deterministic. - The CPU engine's first run no longer prints a spurious advisory line from the model backend's import.
fermion models: one transcribe example in the usage footer.
0.1.21
- Speech on plain CPU:
fermion transcribeand a speechfermion servenow run on x86-64 Linux and Windows, and on a Mac without the MLX runtime.pip install fermion-research torch safetensors soundfile scipy zstandardis the whole setup; the models are the same verified downloads. Apple silicon keeps the MLX engine as its default, andFERMION_DEVICE=cpuselects the CPU engine explicitly. - Transcription decodes deterministically on every engine; transcripts across engines are same-accuracy, not word-identical.
fermion modelsreports which speech engine this machine runs.
0.1.20
- Package documentation copy edits; no behavior change.
fermion models: shorter speech model summaries.
0.1.19
- Package documentation refreshed for the Phonon-1 release.
0.1.18
- Streaming speech over WebSocket: a speech
fermion servealso mountsGET /v1/audio/stream, taking one JSON config frame and then raw mono audio, and answering with partial hypotheses, final segments, and the full transcript on close.--api-keyapplies, as a Bearer header or?api_key=for browser clients. fermion serve --modelpointed at a local speech model directory now serves speech; it previously failed down the chat path.
0.1.17
fermion listen: live dictation from the microphone. Partial hypotheses update one terminal line, a pause finalizes the segment, and Ctrl-C prints the full transcript to standard output.fermion listen --wav FILEstreams a file through the same path paced to real time.fermion --versionreads the installed package metadata instead of a maintained literal.
0.1.16
- Fresh-install fix:
mlx-lmadded to the checked speech runtime and the documented install line. Without it, a first run crashed after the model download instead of printing the install hint.
0.1.15
- Speech support:
fermion transcribeand speech serving with/v1/audio/transcriptions. - Three speech models, downloaded on first use and selected with
--model:FermionResearch/Phonon-1(the default),Phonon-1-Big, andPhonon-1-Micro.
0.1.14
- Native
--draftrouting with no PyTorch model loaded on the optimized path. --draft autoresolves to Neutrino-0.6B.fermion verifydefaults to float32 so PASS matches the identity guarantee.- Clearer reduced-precision near-tie messages.
0.1.13
- More tolerant multi-call envelope parser and private think-block guard.
- Serve-side stuck detector and tool-request sampling profiles.
- Warnings for unsupported OpenAI sampling fields.
- TF32 disabled during CUDA float32 verification.
0.1.12
- Int8 KV column in
inspect. - Clearer YaRN scope and per-model tool-calling guidance.
0.1.11 and earlier
- 0.1.11 added free-space preflight, named disk errors,
FERMION_CACHE_DIR, and post-expansion transport cleanup. - 0.1.10 added KV dtypes, experimental YaRN controls, and session memory guards.
- 0.1.9 added coded Apple Silicon downloads and live prose streaming for tool requests.
- 0.1.8 added unique tool-name aliasing, multiple KV conversations, and session statistics.
- 0.1.7 added OpenAI tools, persistent KV sessions, context clamps, and longer chat output.