mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-31 10:28:43 -04:00
9b893da80f
The SpeakerRecognition short name was 'spkrec', which audio.cpp neither prints nor parses; a name copied out of audio.cpp was rejected and a pinned 'spkrec' would not survive the engine boundary. Emit 'spk', keep 'spkrec' as an input-only alias, and correct the known-tasks lists. Three assertions were vacuous because their fixtures advertised a single task, so reversing a preference order or dropping the RPC name and the attempted pairs from the capability error all passed. Give them fixtures that can tell the orderings apart. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
90 lines
2.4 KiB
C++
90 lines
2.4 KiB
C++
#pragma once
|
|
|
|
// Decides which audio.cpp (task, mode) pair serves a given LocalAI RPC, or
|
|
// produces the capability error when none can. Standard library only, so this
|
|
// unit is tested without an audio.cpp checkout; loaded_model.cpp converts
|
|
// to and from engine::runtime types at the boundary.
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
namespace audiocpp_backend {
|
|
|
|
// Mirrors engine::runtime::VoiceTaskKind, same members and same order.
|
|
enum class Task {
|
|
Vad,
|
|
Asr,
|
|
Diarization,
|
|
SourceSeparation,
|
|
AudioGeneration,
|
|
Tts,
|
|
VoiceCloning,
|
|
VoiceConversion,
|
|
SpeechToSpeech,
|
|
Alignment,
|
|
VoiceDesign,
|
|
SpeakerRecognition,
|
|
Svc,
|
|
};
|
|
|
|
// Mirrors engine::runtime::RunMode.
|
|
enum class Mode { Offline, Streaming };
|
|
|
|
struct TaskCapability {
|
|
Task task = Task::Vad;
|
|
std::vector<Mode> modes;
|
|
};
|
|
|
|
struct Capabilities {
|
|
std::string family;
|
|
std::vector<TaskCapability> tasks;
|
|
};
|
|
|
|
// The LocalAI RPCs this backend serves. The unimplemented ones are not listed:
|
|
// they never reach routing.
|
|
enum class Rpc {
|
|
Tts,
|
|
TtsStream,
|
|
AudioTranscription,
|
|
AudioTranscriptionStream,
|
|
AudioTranscriptionLive,
|
|
Vad,
|
|
Diarize,
|
|
SoundGeneration,
|
|
AudioTransform,
|
|
};
|
|
|
|
struct RequestShape {
|
|
// A speaker reference clip was supplied (TTSRequest.voice resolved to audio).
|
|
bool has_voice_reference = false;
|
|
// TTSRequest.instructions is set.
|
|
bool has_instructions = false;
|
|
// TranscriptRequest.prompt is set.
|
|
bool has_prompt_text = false;
|
|
// The model's `task:` option, empty when unset. Overrides routing.
|
|
std::string pinned_task;
|
|
};
|
|
|
|
struct Route {
|
|
bool ok = false;
|
|
Task task = Task::Tts;
|
|
Mode mode = Mode::Offline;
|
|
// Set when ok is false. Suitable verbatim as an UNIMPLEMENTED message.
|
|
std::string error;
|
|
};
|
|
|
|
Route resolve_route(Rpc rpc, const RequestShape &shape, const Capabilities &caps);
|
|
|
|
// Canonical audio.cpp short names: gen, tts, clon, vc, svc, s2s, asr, align,
|
|
// vad, diar, sep, vdes, spk. parse_task_name additionally accepts "spkrec" as
|
|
// a legacy alias; task_name only ever emits "spk".
|
|
const char *task_name(Task task);
|
|
const char *mode_name(Mode mode);
|
|
const char *rpc_name(Rpc rpc);
|
|
bool parse_task_name(const std::string &value, Task &out);
|
|
|
|
// "asr/offline, asr/streaming", for error messages.
|
|
std::string describe_capabilities(const Capabilities &caps);
|
|
|
|
} // namespace audiocpp_backend
|