mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-05 07:16:10 -04:00
* chore(localvqe): update backend to v1.3, add v1.2/v1.3 gallery models Bump the LocalVQE backend pin 72bfb4c6 -> b0f0378a, which adds the v1.2 (1.3 M) and v1.3 (4.8 M) GGUF SHA-256s to the upstream released-models allowlist (and the arch_version=3 loader) so both load without LOCALVQE_ALLOW_UNHASHED. Add gallery entries for localvqe-v1.2-1.3m and localvqe-v1.3-4.8m (SHA-256 verified against the downloaded weights) and update the audio-transform docs to make v1.3 the current default while noting the compact v1.1/v1.2 alternatives. Assisted-by: Claude:claude-opus-4-8 Claude-Code Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(flake): add ffmpeg-headless to the dev shell pkg/utils/ffmpeg_test.go shells out to the `ffmpeg` CLI, and the pre-commit gate runs those tests via `make test-coverage`. Without ffmpeg in the dev shell the gate fails with "executable file not found in $PATH". The headless build provides the CLI without GUI/X deps. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(localvqe): parse WAV by walking RIFF sub-chunks Walk the RIFF chunk list instead of assuming the canonical 44-byte header layout. Real inputs (browser-recorded clips, ffmpeg output with an 18/40-byte extensible `fmt ` chunk or trailing LIST/INFO metadata) would otherwise splice header/metadata bytes into the PCM stream as an audible impulse. Honour the `data` chunk size and validate that both `fmt ` and `data` chunks are present. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(security-headers): allow blob: in connect-src for waveform fetch The waveform renderer XHRs/fetches a freshly-created blob: object URL (e.g. an uploaded or enhanced clip before it has a server URL). XHR/fetch of blob: is governed by connect-src, not media-src, so it was blocked by the CSP. Add blob: to connect-src. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(react-ui): add input/output spectrogram view to AudioTransform The transform page only showed time-domain amplitude waveforms, so you could see how loud a clip was but not which frequencies the model touched. Add a time x frequency spectrogram heatmap and render the input and output spectrums side by side, so it's visible which bands the enhancement attenuates (bright input bands that go dark in the output). Computed client-side via a Hann-windowed STFT over both clips (a small dependency-free radix-2 FFT), defaulting to the LocalVQE 512/256 frame geometry. This shows the net input->output spectral change; the model's internal gain mask is not exposed by the backend. - src/utils/fft.js radix-2 FFT - src/hooks/useSpectrogram.js decode + STFT -> normalised dB magnitude grid - src/components/audio/Spectrogram.jsx canvas heatmap (magma colormap) - AudioTransform.jsx dual-spectrogram panel + CSS - e2e spec + UI coverage baseline bump (38.29 -> 39.0; measured ~39.4-40.2) Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * test(react-ui): make UI coverage deterministic, tighten the gate UI e2e line coverage swung ~1pp run-to-run (39.1% <-> 40.2%), which forced a loose 0.8pp tolerance on the monotonic gate — a band wide enough to let a real ~300-line regression through silently. The swing was a bug, not inherent jitter: the 'Create Agent navigates' spec ended on the URL assertion, so AgentCreate.jsx's ~400 lines were collected only when its render happened to beat the coverage teardown. Wait for the page to actually render (assert its heading) so those lines are covered every run. With the race gone, repeated runs land within ~0.013pp of each other, so: - tighten UI_COVERAGE_TOLERANCE 0.8 -> 0.1 (noise floor, not a drift band) - set the baseline to the real, reliably-achieved value (39.0 -> 39.86) Localised by running the V8-coverage suite repeatedly and diffing per-file line coverage; AgentCreate.jsx was the sole ~1pp flipper. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com>
136 lines
4.1 KiB
Go
136 lines
4.1 KiB
Go
package audio
|
|
|
|
// Copied from VoxInput
|
|
|
|
import (
|
|
"encoding/binary"
|
|
"io"
|
|
)
|
|
|
|
// WAVHeader represents the WAV file header (44 bytes for PCM)
|
|
type WAVHeader struct {
|
|
// RIFF Chunk (12 bytes)
|
|
ChunkID [4]byte
|
|
ChunkSize uint32
|
|
Format [4]byte
|
|
|
|
// fmt Subchunk (16 bytes)
|
|
Subchunk1ID [4]byte
|
|
Subchunk1Size uint32
|
|
AudioFormat uint16
|
|
NumChannels uint16
|
|
SampleRate uint32
|
|
ByteRate uint32
|
|
BlockAlign uint16
|
|
BitsPerSample uint16
|
|
|
|
// data Subchunk (8 bytes)
|
|
Subchunk2ID [4]byte
|
|
Subchunk2Size uint32
|
|
}
|
|
|
|
func NewWAVHeader(pcmLen uint32) WAVHeader {
|
|
header := WAVHeader{
|
|
ChunkID: [4]byte{'R', 'I', 'F', 'F'},
|
|
Format: [4]byte{'W', 'A', 'V', 'E'},
|
|
Subchunk1ID: [4]byte{'f', 'm', 't', ' '},
|
|
Subchunk1Size: 16, // PCM = 16 bytes
|
|
AudioFormat: 1, // PCM
|
|
NumChannels: 1, // Mono
|
|
SampleRate: 16000,
|
|
ByteRate: 16000 * 2, // SampleRate * BlockAlign (mono, 2 bytes per sample)
|
|
BlockAlign: 2, // 16-bit = 2 bytes per sample
|
|
BitsPerSample: 16,
|
|
Subchunk2ID: [4]byte{'d', 'a', 't', 'a'},
|
|
Subchunk2Size: pcmLen,
|
|
}
|
|
|
|
header.ChunkSize = 36 + header.Subchunk2Size
|
|
|
|
return header
|
|
}
|
|
|
|
func (h *WAVHeader) Write(writer io.Writer) error {
|
|
return binary.Write(writer, binary.LittleEndian, h)
|
|
}
|
|
|
|
// NewWAVHeaderWithRate creates a WAV header for mono 16-bit PCM at the given sample rate.
|
|
func NewWAVHeaderWithRate(pcmLen, sampleRate uint32) WAVHeader {
|
|
header := WAVHeader{
|
|
ChunkID: [4]byte{'R', 'I', 'F', 'F'},
|
|
Format: [4]byte{'W', 'A', 'V', 'E'},
|
|
Subchunk1ID: [4]byte{'f', 'm', 't', ' '},
|
|
Subchunk1Size: 16,
|
|
AudioFormat: 1,
|
|
NumChannels: 1,
|
|
SampleRate: sampleRate,
|
|
ByteRate: sampleRate * 2,
|
|
BlockAlign: 2,
|
|
BitsPerSample: 16,
|
|
Subchunk2ID: [4]byte{'d', 'a', 't', 'a'},
|
|
Subchunk2Size: pcmLen,
|
|
}
|
|
header.ChunkSize = 36 + header.Subchunk2Size
|
|
return header
|
|
}
|
|
|
|
// WAVHeaderSize is the size of a standard PCM WAV header in bytes.
|
|
const WAVHeaderSize = 44
|
|
|
|
// wavDataChunk walks the RIFF sub-chunks of an in-memory WAV and returns the
|
|
// `data` chunk payload (a sub-slice of data, not a copy) plus the sample rate
|
|
// from `fmt `. ok is false when data isn't a RIFF/WAVE stream or carries no
|
|
// data chunk — callers then fall back to treating the input as raw PCM.
|
|
//
|
|
// Walking the chunks rather than assuming the canonical 44-byte header is what
|
|
// keeps an 18/40-byte extensible `fmt `, or JUNK/LIST/bext metadata before or
|
|
// after `data` (e.g. ffmpeg's trailing "Lavf" tag), from being spliced into
|
|
// the PCM as an audible click.
|
|
func wavDataChunk(data []byte) (pcm []byte, sampleRate int, ok bool) {
|
|
if len(data) < 12 || string(data[0:4]) != "RIFF" || string(data[8:12]) != "WAVE" {
|
|
return nil, 0, false
|
|
}
|
|
for off := 12; off+8 <= len(data); {
|
|
id := string(data[off : off+4])
|
|
size := int(binary.LittleEndian.Uint32(data[off+4 : off+8]))
|
|
body := off + 8
|
|
if size < 0 || body+size > len(data) {
|
|
// Truncated/garbage size — clamp to what's left so a short final
|
|
// chunk doesn't drop an otherwise valid data chunk.
|
|
size = len(data) - body
|
|
}
|
|
switch id {
|
|
case "fmt ":
|
|
if size >= 16 {
|
|
sampleRate = int(binary.LittleEndian.Uint32(data[body+4 : body+8]))
|
|
}
|
|
case "data":
|
|
return data[body : body+size], sampleRate, true
|
|
}
|
|
// Chunks are word-aligned: an odd size is followed by a pad byte.
|
|
off = body + size + (size & 1)
|
|
}
|
|
return nil, 0, false
|
|
}
|
|
|
|
// StripWAVHeader removes a WAV header from audio data, returning raw PCM. If
|
|
// the data isn't a recognisable WAV (e.g. it's already raw PCM) it is returned
|
|
// unchanged. Locates the `data` chunk by walking the RIFF structure rather
|
|
// than assuming a fixed 44-byte header — see [wavDataChunk].
|
|
func StripWAVHeader(data []byte) []byte {
|
|
if pcm, _, ok := wavDataChunk(data); ok {
|
|
return pcm
|
|
}
|
|
return data
|
|
}
|
|
|
|
// ParseWAV returns the raw PCM of a WAV's `data` chunk along with the sample
|
|
// rate from `fmt `. If the data isn't a recognisable WAV it is returned as-is
|
|
// with sampleRate=0. Walks the RIFF structure — see [wavDataChunk].
|
|
func ParseWAV(data []byte) (pcm []byte, sampleRate int) {
|
|
if pcm, sr, ok := wavDataChunk(data); ok {
|
|
return pcm, sr
|
|
}
|
|
return data, 0
|
|
}
|