60615db4ed
Squash of 54 work commits (Sep 1–12):6251f7cai-hub: body domain — live pose packets ride the realtime sessionea50c77chat_ui: the feed's session gets its profile brief backf51b5f3ai-body: the crate for the native SAM 3D Body port, with its weights reader8211ae6ai-body: the MHR rig and the pose head's parameter decoding, oracle-exact9e343a8ai-body: the DINOv3 ViT-H+/16 backbone, crop and ray conditioning; Metal gains rope-half and affine layer norm69d842cai-body: the promptable pose decoder and its refinement loop, oracle-matched on Metal66e5e2fai-hub: SAM 3D Body runs natively — `sam3dbody` on the body domain, oracle-matched end to enda634198ai-hub: the body-native commit carried a peer's in-flight hub hunks; put them back where they were9ff44e8ai-hub: the body-native wiring, this time only the lane's hunks6a1c16bai-body: third-party notices — what the port is implemented after, and what it is notd78411aai-body: the per-step work moves to the GPUb22259bai-body: the context stays on the GPU; only the pose token leaves the loop346f31fai-body: flash attention for the head-dim-64 blocks45b5b98ai-body: the crop size is a runtime knob, and the loop reports where its time goes4be6d19ai-body: the test modules import the grid constants they still use7598346ai-body: tensor-core GEMMs for the backbone, and the rig's correctives only where they counta9ce596ai-body: the crop warp runs across cores8964ba6ai-body: an FP8 backbone mode, off by default, measured against the oraclea2aaa8fai-body: the FP8 bias rides a column-broadcast add on the deviced53c77dmetal: a device-resident ViT stack, and the body backbone rides itd006d0ametal: resident f32 linears keep their weight on the device525ba1cmetal: a device-resident two-way decoder layer, and the body decoder rides itc9e6d88ai-body: the hands pass — hand crops, the hand decoder, the hand-mode rig and the wrist fusion62dff26ai-body: the mask prompt — a person's segmentation mask conditions the body passa648cf8ai-hub: body session options — hands, detect, persons=N8c568dfai-hub: drop the SAM 3D Body reference worker backend7ff875aai-hub: keep a peer's in-flight beats/notes/local work out of the body commits31e5faaai-hub: local model runner, licence acknowledgements, a shared install panel; Beat This!, Basic Pitch and the Salamander drum-kit entriesb94bc58ai-services: the wire, the app port and the panel state — one conversation, many apps2acb798ai-services: wire v2 — endpoints, receiver-side caps, result disposition8ae0ffbai-services: the engine core — registry, router and conversation, tested against a scripted model2308736ai-services: the real models behind the engine feature — local through the hub, Claude, and nonec3f631dlivepipe: one reusable pipe from a camera to a fleet node and backff62db3ai libs: the runtime env-var cleanup — precision is a per-caller policy, not an environment side channel04a94efrealtime: one service-log line when a live session opens and one when it closes0ecb81cai models: the model-crates env-var cleanup — 172 research knobs gone, the unset default is the code4ca36c1ai hub + services: the assistant's model comes from wherever it is resident — the fleet chat box, with tools, then the local weights432121eaichat engine + wm: launch, then use — the assistant continues in the same turn once the app it started is on the bus7a5bf69ai-hub registry: the Salamander drumkit samples come from the makepad.nl mirror — the GitHub repo only carries the .sfz files102ffc5ai-services: messages on the bus — a manifest declares topics, the engine subscribes on a tool's behalf or by ToolResult.subscribe, a service publishes Message frames, an idle conversation wakes on a message as an event turn under rate laws; the WM bus forwards the new frames; every app that matches the wire gets its arma837792hub + flow: a whitespace-only chat completion is retried once and then fails instead of passing as an answer; a flow's model is a fleet model id unless it names a weight file on disk; chat models show under the text domain in /v1/modelsbc6c620hub + flow: what the chat review found — the in-process route retries an empty completion too, a node says whether its prefill opened thinking so a brief-mode answer is never discarded, a preferred model falls back to normal election when no node has it, discovery keeps looking for the preferred model until patience runs out75c3441hub: the PRO 6000 serves image as well as chat and textad5e98bhub registry: flux2-dev's VRAM estimate is its measured peak, 30 GBc7241e0hub: a node that evicted every resident releases its cached allocator pool before refusing a load or publishing usable VRAM30575f0flow: route generation by request workload1be1e21ai-hub: gate downloads by disk capacity and recover fleet admission df6b394 filesystem_watcher, bounded_http, ai services: live and tool prerequisites 79ebdb9 ai-hub: add a native Pixal3D image-to-3D backend 0ba0d74 ai-hub: propagate typed refusals under reject queue policy cc6c872 Speed up H3 conditioning and video decoding e512059 Fix Qwen vision residency and generated material colors 2864f68 ai-hub http client: bound every plain TCP connect to 3 s per address 3d93229 ai: CUDA is a Linux/Windows-only dependency; the hub library defaults to llm + stt Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
73 lines
2 KiB
TOML
73 lines
2 KiB
TOML
[package]
|
|
name = "makepad-ai-speech"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Speech family: IndexTTS-2.5 + Kokoro speech synthesis engines (text in, PCM out). No platform code: OS voices are makepad-system-speech, engine choice is makepad-ai-hub."
|
|
license = "MIT"
|
|
|
|
[features]
|
|
default = ["whisper", "vad", "kokoro", "indextts"]
|
|
# Whisper speech-to-text (CPU SIMD / Metal / CUDA).
|
|
whisper = []
|
|
# Silero voice-activity detection.
|
|
vad = []
|
|
# Kokoro-82M text-to-speech (+ its G2P).
|
|
kokoro = []
|
|
# IndexTTS-2.5 character-voice text-to-speech.
|
|
indextts = []
|
|
# Precompile the Whisper ggml Metal library at build time (else runtime source compile).
|
|
metal-precompile = []
|
|
|
|
[dependencies]
|
|
# THE CUDA store (Whisper's CUDA backend). Must NOT be target-specific: cargo
|
|
# drops target-cfg deps when this crate is a path dep of another standalone
|
|
# `[workspace]`, and the `links = "makepad_ai_cuda"` handshake
|
|
# (DEP_MAKEPAD_AI_CUDA_KERNELS, read in build.rs) only arrives for an
|
|
# unconditional dependency. On macOS/iOS the crate compiles to empty stubs.
|
|
makepad-ai-cuda = { path = "../../cuda" }
|
|
makepad-ai-common = { path = "../common" }
|
|
makepad-ai-loader = { path = "../../loader" }
|
|
makepad-ai-sfx = { path = "../sfx" }
|
|
|
|
[[bin]]
|
|
name = "g2p_test"
|
|
path = "src/bin/g2p_test.rs"
|
|
required-features = ["kokoro"]
|
|
|
|
[[bin]]
|
|
name = "har_bisect"
|
|
path = "src/bin/har_bisect.rs"
|
|
required-features = ["kokoro"]
|
|
|
|
[[bin]]
|
|
name = "kokoro_probe"
|
|
path = "src/bin/kokoro_probe.rs"
|
|
required-features = ["kokoro"]
|
|
|
|
[[bin]]
|
|
name = "parity"
|
|
path = "src/bin/parity.rs"
|
|
required-features = ["kokoro"]
|
|
|
|
[[bin]]
|
|
name = "tts_test"
|
|
path = "src/bin/tts_test.rs"
|
|
required-features = ["kokoro"]
|
|
|
|
[target.'cfg(any(target_os = "macos", target_os = "ios"))'.dependencies]
|
|
makepad-objc-sys = { path = "../../../objc-sys", version = "1.0.0" }
|
|
|
|
[[bin]]
|
|
name = "whisper-test"
|
|
path = "src/bin/whisper_test.rs"
|
|
required-features = ["whisper"]
|
|
|
|
[[bin]]
|
|
name = "vad-test"
|
|
path = "src/bin/vad_test.rs"
|
|
required-features = ["vad"]
|
|
|
|
[[bin]]
|
|
name = "metal-strip-unused"
|
|
path = "src/bin/metal_strip_unused.rs"
|
|
required-features = ["whisper"]
|