-
Notifications
You must be signed in to change notification settings - Fork 470
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add speaker identification APIs for HarmonyOS (#1607)
* Add speaker embedding extractor API for HarmonyOS * Add ArkTS API for speaker identification
- Loading branch information
1 parent
a743a44
commit 314545f
Showing
19 changed files
with
374 additions
and
60 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
139 changes: 139 additions & 0 deletions
139
harmony-os/SherpaOnnxHar/sherpa_onnx/src/main/ets/components/SpeakerIdentification.ets
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,139 @@ | ||
| import { | ||
| createSpeakerEmbeddingExtractor, | ||
| createSpeakerEmbeddingManager, | ||
| speakerEmbeddingExtractorComputeEmbedding, | ||
| speakerEmbeddingExtractorCreateStream, | ||
| speakerEmbeddingExtractorDim, | ||
| speakerEmbeddingExtractorIsReady, | ||
| speakerEmbeddingManagerAdd, | ||
| speakerEmbeddingManagerAddListFlattened, | ||
| speakerEmbeddingManagerContains, | ||
| speakerEmbeddingManagerGetAllSpeakers, | ||
| speakerEmbeddingManagerNumSpeakers, | ||
| speakerEmbeddingManagerRemove, | ||
| speakerEmbeddingManagerSearch, | ||
| speakerEmbeddingManagerVerify | ||
| } from 'libsherpa_onnx.so'; | ||
| import { OnlineStream } from './StreamingAsr'; | ||
|
|
||
| export class SpeakerEmbeddingExtractorConfig { | ||
| public model: string = ''; | ||
| public numThreads: number = 1; | ||
| public debug: boolean = false; | ||
| public provider: string = 'cpu'; | ||
| } | ||
|
|
||
| export class SpeakerEmbeddingExtractor { | ||
| public config: SpeakerEmbeddingExtractorConfig = new SpeakerEmbeddingExtractorConfig(); | ||
| public dim: number; | ||
| private handle: object; | ||
|
|
||
| constructor(config: SpeakerEmbeddingExtractorConfig, mgr?: object) { | ||
| this.handle = createSpeakerEmbeddingExtractor(config, mgr); | ||
| this.config = config; | ||
| this.dim = speakerEmbeddingExtractorDim(this.handle); | ||
| } | ||
|
|
||
| createStream(): OnlineStream { | ||
| return new OnlineStream( | ||
| speakerEmbeddingExtractorCreateStream(this.handle)); | ||
| } | ||
|
|
||
| isReady(stream: OnlineStream): boolean { | ||
| return speakerEmbeddingExtractorIsReady(this.handle, stream.handle); | ||
| } | ||
|
|
||
| compute(stream: OnlineStream, enableExternalBuffer: boolean = true): Float32Array { | ||
| return speakerEmbeddingExtractorComputeEmbedding( | ||
| this.handle, stream.handle, enableExternalBuffer); | ||
| } | ||
| } | ||
|
|
||
| function flatten(arrayList: Float32Array[]): Float32Array { | ||
| let n = 0; | ||
| for (let i = 0; i < arrayList.length; ++i) { | ||
| n += arrayList[i].length; | ||
| } | ||
| let ans = new Float32Array(n); | ||
|
|
||
| let offset = 0; | ||
| for (let i = 0; i < arrayList.length; ++i) { | ||
| ans.set(arrayList[i], offset); | ||
| offset += arrayList[i].length; | ||
| } | ||
| return ans; | ||
| } | ||
|
|
||
| interface SpeakerNameWithEmbedding { | ||
| name: string; | ||
| v: Float32Array; | ||
| } | ||
|
|
||
| interface SpeakerNameWithEmbeddingList { | ||
| name: string; | ||
| v: Float32Array[]; | ||
| } | ||
|
|
||
| interface SpeakerNameWithEmbeddingN { | ||
| name: string; | ||
| vv: Float32Array; | ||
| n: number; | ||
| } | ||
|
|
||
| interface EmbeddingWithThreshold { | ||
| v: Float32Array; | ||
| threshold: number; | ||
| } | ||
|
|
||
| interface SpeakerNameEmbeddingThreshold { | ||
| name: string; | ||
| v: Float32Array; | ||
| threshold: number; | ||
| } | ||
|
|
||
| export class SpeakerEmbeddingManager { | ||
| public dim: number; | ||
| private handle: object; | ||
|
|
||
| constructor(dim: number) { | ||
| this.handle = createSpeakerEmbeddingManager(dim); | ||
| this.dim = dim; | ||
| } | ||
|
|
||
| add(speaker: SpeakerNameWithEmbedding): boolean { | ||
| return speakerEmbeddingManagerAdd(this.handle, speaker); | ||
| } | ||
|
|
||
| addMulti(speaker: SpeakerNameWithEmbeddingList): boolean { | ||
| const c: SpeakerNameWithEmbeddingN = { | ||
| name: speaker.name, | ||
| vv: flatten(speaker.v), | ||
| n: speaker.v.length, | ||
| }; | ||
| return speakerEmbeddingManagerAddListFlattened(this.handle, c); | ||
| } | ||
|
|
||
| remove(name: string): boolean { | ||
| return speakerEmbeddingManagerRemove(this.handle, name); | ||
| } | ||
|
|
||
| search(obj: EmbeddingWithThreshold): string { | ||
| return speakerEmbeddingManagerSearch(this.handle, obj); | ||
| } | ||
|
|
||
| verify(obj: SpeakerNameEmbeddingThreshold): boolean { | ||
| return speakerEmbeddingManagerVerify(this.handle, obj); | ||
| } | ||
|
|
||
| contains(name: string): boolean { | ||
| return speakerEmbeddingManagerContains(this.handle, name); | ||
| } | ||
|
|
||
| getNumSpeakers(): number { | ||
| return speakerEmbeddingManagerNumSpeakers(this.handle); | ||
| } | ||
|
|
||
| getAllSpeakerNames(): string[] { | ||
| return speakerEmbeddingManagerGetAllSpeakers(this.handle); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.