experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #3012 from reuben/index-ts

Browse Source 
Switch index.js to TypeScript
This commit is contained in:
Reuben Morais 2020-05-25 19:57:02 +02:00 committed by GitHub
commit b12c7be710
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
12 changed files with 327 additions and 543 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
doc/Makefile
View File

@ -29,7 +29,7 @@ pip3:
$(PIP_INSTALL) -r ../taskcluster/docs-requirements.txt $(PIP_INSTALL) -r ../taskcluster/docs-requirements.txt
npm: npm:
npm install jsdoc@3.6.3 npm install typedoc@0.17.4 typescript@3.8.3 @types/node@13.9.x
submodule: submodule:
git submodule update --init --remote git submodule update --init --remote

2
doc/NodeJS-API.rst
View File

@ -1,8 +1,6 @@
JavaScript (NodeJS / ElectronJS) JavaScript (NodeJS / ElectronJS)
================================ ================================
Support for TypeScript is :download:`provided in index.d.ts<../native_client/javascript/index.d.ts>`
Model Model
----- -----

4
doc/conf.py
View File

@ -80,7 +80,9 @@ breathe_projects = {
"deepspeech-dotnet": "xml-dotnet/", "deepspeech-dotnet": "xml-dotnet/",
} }
js_source_path = "../native_client/javascript" js_source_path = "../native_client/javascript/index.ts"
js_language = "typescript"
jsdoc_config_path = "../native_client/javascript/tsconfig.json"
# Add any paths that contain templates here, relative to this directory. # Add any paths that contain templates here, relative to this directory.
templates_path = ['.templates'] templates_path = ['.templates']

2
native_client/javascript/Makefile
View File

@ -59,7 +59,7 @@ copy-deps: build
node-wrapper: copy-deps build node-wrapper: copy-deps build
PATH="$(NODE_MODULES_BIN):${PATH}" $(NODE_BUILD_TOOL) $(NODE_PLATFORM_TARGET) $(NODE_RUNTIME) $(NODE_ABI_TARGET) $(NODE_DIST_URL) --no-color package $(NODE_BUILD_VERBOSE) PATH="$(NODE_MODULES_BIN):${PATH}" $(NODE_BUILD_TOOL) $(NODE_PLATFORM_TARGET) $(NODE_RUNTIME) $(NODE_ABI_TARGET) $(NODE_DIST_URL) --no-color package $(NODE_BUILD_VERBOSE)
npm-pack: clean package.json index.js npm-dev npm-pack: clean package.json index.ts npm-dev
PATH="$(NODE_MODULES_BIN):${PATH}" tsc && $(NPM_TOOL) pack $(NODE_BUILD_VERBOSE) PATH="$(NODE_MODULES_BIN):${PATH}" tsc && $(NPM_TOOL) pack $(NODE_BUILD_VERBOSE)
deepspeech_wrap.cxx: deepspeech.i ds-swig deepspeech_wrap.cxx: deepspeech.i ds-swig

2
native_client/javascript/client.ts
View File

@ -3,7 +3,7 @@
// This is required for process.versions.electron below // This is required for process.versions.electron below
/// <reference types="electron" /> /// <reference types="electron" />
import Ds from "./index"; import * as Ds from "./index";
import * as Fs from "fs"; import * as Fs from "fs";
import Sox from "sox-stream"; import Sox from "sox-stream";
import * as argparse from "argparse"; import * as argparse from "argparse";

196
native_client/javascript/index.d.ts vendored
View File

@ -1,196 +0,0 @@
/**
* Stores text of an individual token, along with its timing information
*/
export interface TokenMetadata {
text: string;
timestep: number;
start_time: number;
}
/**
* A single transcript computed by the model, including a confidence value and
* the metadata for its constituent tokens.
*/
export interface CandidateTranscript {
tokens: TokenMetadata[];
confidence: number;
}
/**
* An array of CandidateTranscript objects computed by the model.
*/
export interface Metadata {
transcripts: CandidateTranscript[];
}
/**
* An object providing an interface to a trained DeepSpeech model.
*
* @param aModelPath The path to the frozen model graph.
*
* @throws on error
*/
export class Model {
constructor(aModelPath: string)
/**
* Get beam width value used by the model. If :js:func:Model.setBeamWidth was
* not called before, will return the default value loaded from the model file.
*
* @return Beam width value used by the model.
*/
beamWidth(): number;
/**
* Set beam width value used by the model.
*
* @param The beam width used by the model. A larger beam width value generates better results at the cost of decoding time.
*
* @return Zero on success, non-zero on failure.
*/
setBeamWidth(aBeamWidth: number): number;
/**
* Return the sample rate expected by the model.
*
* @return Sample rate.
*/
sampleRate(): number;
/**
* Enable decoding using an external scorer.
*
* @param aScorerPath The path to the external scorer file.
*
* @return Zero on success, non-zero on failure (invalid arguments).
*/
enableExternalScorer(aScorerPath: string): number;
/**
* Disable decoding using an external scorer.
*
* @return Zero on success, non-zero on failure (invalid arguments).
*/
disableExternalScorer(): number;
/**
* Set hyperparameters alpha and beta of the external scorer.
*
* @param aLMAlpha The alpha hyperparameter of the CTC decoder. Language Model weight.
* @param aLMBeta The beta hyperparameter of the CTC decoder. Word insertion weight.
*
* @return Zero on success, non-zero on failure (invalid arguments).
*/
setScorerAlphaBeta(aLMAlpha: number, aLMBeta: number): number;
/**
* Use the DeepSpeech model to perform Speech-To-Text.
*
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
*
* @return The STT result. Returns undefined on error.
*/
stt(aBuffer: Buffer): string;
/**
* Use the DeepSpeech model to perform Speech-To-Text and output metadata
* about the results.
*
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
* @param aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this.
* Default value is 1 if not specified.
*
* @return :js:func:`Metadata` object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information.
* The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
*/
sttWithMetadata(aBuffer: Buffer, aNumResults?: number): Metadata;
/**
* Create a new streaming inference state. One can then call :js:func:`Stream.feedAudioContent` and :js:func:`Stream.finishStream` on the returned stream object.
*
* @return a :js:func:`Stream` object that represents the streaming state.
*
* @throws on error
*/
createStream(): Stream;
}
/**
* @class
* Provides an interface to a DeepSpeech stream. The constructor cannot be called
* directly, use :js:func:`Model.createStream`.
*/
declare class Stream {
/**
* Feed audio samples to an ongoing streaming inference.
*
* @param aBuffer An array of 16-bit, mono raw audio samples at the
* appropriate sample rate (matching what the model was trained on).
*/
feedAudioContent(aBuffer: Buffer): void;
/**
* Compute the intermediate decoding of an ongoing streaming inference.
*
* @return The STT intermediate result.
*/
intermediateDecode(): string;
/**
* Compute the intermediate decoding of an ongoing streaming inference, return results including metadata.
*
* @param aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return :js:func:`Metadata` object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
*/
intermediateDecodeWithMetadata (aNumResults?: number): Metadata;
/**
* Compute the final decoding of an ongoing streaming inference and return the result. Signals the end of an ongoing streaming inference.
*
* @return The STT result.
*
* This method will free the stream, it must not be used after this method is called.
*/
finishStream(): string;
/**
* Compute the final decoding of an ongoing streaming inference and return the results including metadata. Signals the end of an ongoing streaming inference.
*
* @param aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return Outputs a :js:func:`Metadata` struct of individual letters along with their timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`.
*
* This method will free the stream, it must not be used after this method is called.
*/
finishStreamWithMetadata(aNumResults?: number): Metadata;
}
/**
* Frees associated resources and destroys model object.
*
* @param model A model pointer returned by :js:func:`Model`
*
*/
export function FreeModel(model: Model): void;
/**
* Free memory allocated for metadata information.
*
* @param metadata Object containing metadata as returned by :js:func:`Model.sttWithMetadata` or :js:func:`Stream.finishStreamWithMetadata`
*/
export function FreeMetadata(metadata: Metadata): void;
/**
* Destroy a streaming state without decoding the computed logits. This
* can be used if you no longer need the result of an ongoing streaming
* inference and don't want to perform a costly decode operation.
*
* @param stream A streaming state pointer returned by :js:func:`Model.createStream`.
*/
export function FreeStream(stream: Stream): void;
/**
* Print version of this library and of the linked TensorFlow library on standard output.
*/
export function Version(): void;

336
native_client/javascript/index.js
View File

@ -1,336 +0,0 @@
'use strict';
const binary = require('node-pre-gyp');
const path = require('path')
// 'lib', 'binding', 'v0.1.1', ['node', 'v' + process.versions.modules, process.platform, process.arch].join('-'), 'deepspeech-bindings.node')
const binding_path = binary.find(path.resolve(path.join(__dirname, 'package.json')));
// On Windows, we can't rely on RPATH being set to $ORIGIN/../ or on
// @loader_path/../ but we can change the PATH to include the proper directory
// for the dynamic linker
if (process.platform === 'win32') {
const dslib_path = path.resolve(path.join(binding_path, '../..'));
var oldPath = process.env.PATH;
process.env['PATH'] = `${dslib_path};${process.env.PATH}`;
}
const binding = require(binding_path);
if (process.platform === 'win32') {
process.env['PATH'] = oldPath;
}
/**
* @class
* An object providing an interface to a trained DeepSpeech model.
*
* @param {string} aModelPath The path to the frozen model graph.
*
* @throws on error
*/
function Model(aModelPath) {
this._impl = null;
const rets = binding.CreateModel(aModelPath);
const status = rets[0];
const impl = rets[1];
if (status !== 0) {
throw "CreateModel failed with '"+binding.ErrorCodeToErrorMessage(status)+"' (0x" + status.toString(16) + ")";
}
this._impl = impl;
}
/**
* Get beam width value used by the model. If :js:func:Model.setBeamWidth was
* not called before, will return the default value loaded from the model file.
*
* @return {number} Beam width value used by the model.
*/
Model.prototype.beamWidth = function() {
return binding.GetModelBeamWidth(this._impl);
}
/**
* Set beam width value used by the model.
*
* @param {number} The beam width used by the model. A larger beam width value generates better results at the cost of decoding time.
*
* @return {number} Zero on success, non-zero on failure.
*/
Model.prototype.setBeamWidth = function(aBeamWidth) {
return binding.SetModelBeamWidth(this._impl, aBeamWidth);
}
/**
* Return the sample rate expected by the model.
*
* @return {number} Sample rate.
*/
Model.prototype.sampleRate = function() {
return binding.GetModelSampleRate(this._impl);
}
/**
* Enable decoding using an external scorer.
*
* @param {string} aScorerPath The path to the external scorer file.
*
* @throws on error
*/
Model.prototype.enableExternalScorer = function(aScorerPath) {
const status = binding.EnableExternalScorer(this._impl, aScorerPath);
if (status !== 0) {
throw "EnableExternalScorer failed with '"+binding.ErrorCodeToErrorMessage(status)+"' (0x" + status.toString(16) + ")";
}
}
/**
* Disable decoding using an external scorer.
*
* @return {number} Zero on success, non-zero on failure (invalid arguments).
*/
Model.prototype.disableExternalScorer = function() {
return binding.EnableExternalScorer(this._impl);
}
/**
* Set hyperparameters alpha and beta of the external scorer.
*
* @param {float} aLMAlpha The alpha hyperparameter of the CTC decoder. Language Model weight.
* @param {float} aLMBeta The beta hyperparameter of the CTC decoder. Word insertion weight.
*
* @return {number} Zero on success, non-zero on failure (invalid arguments).
*/
Model.prototype.setScorerAlphaBeta = function(aLMAlpha, aLMBeta) {
return binding.SetScorerAlphaBeta(this._impl, aLMAlpha, aLMBeta);
}
/**
* Use the DeepSpeech model to perform Speech-To-Text.
*
* @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
*
* @return {string} The STT result. Returns undefined on error.
*/
Model.prototype.stt = function(aBuffer) {
return binding.SpeechToText(this._impl, aBuffer);
}
/**
* Use the DeepSpeech model to perform Speech-To-Text and output results including metadata.
*
* @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
* @param {number} aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return {object} :js:func:`Metadata` object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
*/
Model.prototype.sttWithMetadata = function(aBuffer, aNumResults) {
aNumResults = aNumResults || 1;
return binding.SpeechToTextWithMetadata(this._impl, aBuffer, aNumResults);
}
/**
* Create a new streaming inference state. One can then call :js:func:`Stream.feedAudioContent` and :js:func:`Stream.finishStream` on the returned stream object.
*
* @return {object} a :js:func:`Stream` object that represents the streaming state.
*
* @throws on error
*/
Model.prototype.createStream = function() {
const rets = binding.CreateStream(this._impl);
const status = rets[0];
const ctx = rets[1];
if (status !== 0) {
throw "CreateStream failed with '"+binding.ErrorCodeToErrorMessage(status)+"' (0x" + status.toString(16) + ")";
}
return new Stream(ctx);
}
/**
* @class
* Provides an interface to a DeepSpeech stream. The constructor cannot be called
* directly, use :js:func:`Model.createStream`.
*/
function Stream(nativeStream) {
this._impl = nativeStream;
}
/**
* Feed audio samples to an ongoing streaming inference.
*
* @param {buffer} aBuffer An array of 16-bit, mono raw audio samples at the
* appropriate sample rate (matching what the model was trained on).
*/
Stream.prototype.feedAudioContent = function(aBuffer) {
binding.FeedAudioContent(this._impl, aBuffer);
}
/**
* Compute the intermediate decoding of an ongoing streaming inference.
*
* @return {string} The STT intermediate result.
*/
Stream.prototype.intermediateDecode = function() {
return binding.IntermediateDecode(this._impl);
}
/**
* Compute the intermediate decoding of an ongoing streaming inference, return results including metadata.
*
* @param {number} aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return {object} :js:func:`Metadata` object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
*/
Stream.prototype.intermediateDecodeWithMetadata = function(aNumResults) {
aNumResults = aNumResults || 1;
return binding.IntermediateDecodeWithMetadata(this._impl, aNumResults);
}
/**
* Compute the final decoding of an ongoing streaming inference and return the result. Signals the end of an ongoing streaming inference.
*
* @return {string} The STT result.
*
* This method will free the stream, it must not be used after this method is called.
*/
Stream.prototype.finishStream = function() {
let result = binding.FinishStream(this._impl);
this._impl = null;
return result;
}
/**
* Compute the final decoding of an ongoing streaming inference and return the results including metadata. Signals the end of an ongoing streaming inference.
*
* @param {number} aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return {object} Outputs a :js:func:`Metadata` struct of individual letters along with their timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`.
*
* This method will free the stream, it must not be used after this method is called.
*/
Stream.prototype.finishStreamWithMetadata = function(aNumResults) {
aNumResults = aNumResults || 1;
let result = binding.FinishStreamWithMetadata(this._impl, aNumResults);
this._impl = null;
return result;
}
/**
* Frees associated resources and destroys model object.
*
* @param {object} model A model pointer returned by :js:func:`Model`
*
*/
function FreeModel(model) {
return binding.FreeModel(model._impl);
}
/**
* Free memory allocated for metadata information.
*
* @param {object} metadata Object containing metadata as returned by :js:func:`Model.sttWithMetadata` or :js:func:`Stream.finishStreamWithMetadata`
*/
function FreeMetadata(metadata) {
return binding.FreeMetadata(metadata);
}
/**
* Destroy a streaming state without decoding the computed logits. This
* can be used if you no longer need the result of an ongoing streaming
* inference and don't want to perform a costly decode operation.
*
* @param {Object} stream A stream object returned by :js:func:`Model.createStream`.
*/
function FreeStream(stream) {
return binding.FreeStream(stream._impl);
}
/**
* Print version of this library and of the linked TensorFlow library on standard output.
*/
function Version() {
return binding.Version();
}
//// Metadata, CandidateTranscript and TokenMetadata are here only for documentation purposes
/**
* @class
*
* Stores text of an individual token, along with its timing information
*/
function TokenMetadata() {}
/**
* The text corresponding to this token
*
* @return {string} The text generated
*/
TokenMetadata.prototype.text = function() {}
/**
* Position of the token in units of 20ms
*
* @return {int} The position of the token
*/
TokenMetadata.prototype.timestep = function() {};
/**
* Position of the token in seconds
*
* @return {float} The position of the token
*/
TokenMetadata.prototype.start_time = function() {};
/**
* @class
*
* A single transcript computed by the model, including a confidence value and
* the metadata for its constituent tokens.
*/
function CandidateTranscript () {}
/**
* Array of tokens
*
* @return {array} Array of :js:func:`TokenMetadata`
*/
CandidateTranscript.prototype.tokens = function() {}
/**
* Approximated confidence value for this transcription. This is roughly the
* sum of the acoustic model logit values for each timestep/token that
* contributed to the creation of this transcription.
*
* @return {float} Confidence value
*/
CandidateTranscript.prototype.confidence = function() {}
/**
* @class
*
* An array of CandidateTranscript objects computed by the model.
*/
function Metadata () {}
/**
* Array of transcripts
*
* @return {array} Array of :js:func:`CandidateTranscript` objects
*/
Metadata.prototype.transcripts = function() {}
module.exports = {
Model: Model,
Metadata: Metadata,
CandidateTranscript: CandidateTranscript,
TokenMetadata: TokenMetadata,
Version: Version,
FreeModel: FreeModel,
FreeStream: FreeStream,
FreeMetadata: FreeMetadata
};

307
native_client/javascript/index.ts Normal file
View File

@ -0,0 +1,307 @@
import binary from 'node-pre-gyp';
import path from 'path';
// 'lib', 'binding', 'v0.1.1', ['node', 'v' + process.versions.modules, process.platform, process.arch].join('-'), 'deepspeech-bindings.node')
const binding_path = binary.find(path.resolve(path.join(__dirname, 'package.json')));
// On Windows, we can't rely on RPATH being set to $ORIGIN/../ or on
// @loader_path/../ but we can change the PATH to include the proper directory
// for the dynamic linker
if (process.platform === 'win32') {
const dslib_path = path.resolve(path.join(binding_path, '../..'));
var oldPath = process.env.PATH;
process.env['PATH'] = `${dslib_path};${process.env.PATH}`;
}
const binding = require(binding_path);
if (process.platform === 'win32') {
process.env['PATH'] = oldPath;
}
/**
* Stores text of an individual token, along with its timing information
*/
export interface TokenMetadata {
/** The text corresponding to this token */
text: string;
/** Position of the token in units of 20ms */
timestep: number;
/** Position of the token in seconds */
start_time: number;
}
/**
* A single transcript computed by the model, including a confidence value and
* the metadata for its constituent tokens.
*/
export interface CandidateTranscript {
tokens: TokenMetadata[];
/**
* Approximated confidence value for this transcription. This is roughly the
* sum of the acoustic model logit values for each timestep/token that
* contributed to the creation of this transcription.
*/
confidence: number;
}
/**
* An array of CandidateTranscript objects computed by the model.
*/
export interface Metadata {
transcripts: CandidateTranscript[];
}
/**
* Provides an interface to a DeepSpeech stream. The constructor cannot be called
* directly, use :js:func:`Model.createStream`.
*/
class Stream {
/** @internal */
_impl: any;
/**
* @param nativeStream SWIG wrapper for native StreamingState object.
*/
constructor(nativeStream: object) {
this._impl = nativeStream;
}
/**
* Feed audio samples to an ongoing streaming inference.
*
* @param aBuffer An array of 16-bit, mono raw audio samples at the
* appropriate sample rate (matching what the model was trained on).
*/
feedAudioContent(aBuffer: Buffer): void {
binding.FeedAudioContent(this._impl, aBuffer);
}
/**
* Compute the intermediate decoding of an ongoing streaming inference.
*
* @return The STT intermediate result.
*/
intermediateDecode(): string {
return binding.IntermediateDecode(this._impl);
}
/**
* Compute the intermediate decoding of an ongoing streaming inference, return results including metadata.
*
* @param aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return :js:func:`Metadata` object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
*/
intermediateDecodeWithMetadata(aNumResults: number = 1): Metadata {
return binding.IntermediateDecodeWithMetadata(this._impl, aNumResults);
}
/**
* Compute the final decoding of an ongoing streaming inference and return the result. Signals the end of an ongoing streaming inference.
*
* @return The STT result.
*
* This method will free the stream, it must not be used after this method is called.
*/
finishStream(): string {
const result = binding.FinishStream(this._impl);
this._impl = null;
return result;
}
/**
* Compute the final decoding of an ongoing streaming inference and return the results including metadata. Signals the end of an ongoing streaming inference.
*
* @param aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this. Default value is 1 if not specified.
*
* @return Outputs a :js:func:`Metadata` struct of individual letters along with their timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`.
*
* This method will free the stream, it must not be used after this method is called.
*/
finishStreamWithMetadata(aNumResults: number = 1): Metadata {
const result = binding.FinishStreamWithMetadata(this._impl, aNumResults);
this._impl = null;
return result;
}
}
/**
* An object providing an interface to a trained DeepSpeech model.
*/
export class Model {
/** @internal */
_impl: any;
/**
* @param aModelPath The path to the frozen model graph.
*
* @throws on error
*/
constructor(aModelPath: string) {
this._impl = null;
const [status, impl] = binding.CreateModel(aModelPath);
if (status !== 0) {
throw `CreateModel failed: ${binding.ErrorCodeToErrorMessage(status)} (0x${status.toString(16)})`;
}
this._impl = impl;
}
/**
* Get beam width value used by the model. If :js:func:`Model.setBeamWidth` was
* not called before, will return the default value loaded from the model file.
*
* @return Beam width value used by the model.
*/
beamWidth(): number {
return binding.GetModelBeamWidth(this._impl);
}
/**
* Set beam width value used by the model.
*
* @param aBeamWidth The beam width used by the model. A larger beam width value generates better results at the cost of decoding time.
*
* @throws on error
*/
setBeamWidth(aBeamWidth: number): void {
const status = binding.SetModelBeamWidth(this._impl, aBeamWidth);
if (status !== 0) {
throw `SetModelBeamWidth failed: ${binding.ErrorCodeToErrorMessage(status)} (0x${status.toString(16)})`;
}
}
/**
* Return the sample rate expected by the model.
*
* @return Sample rate.
*/
sampleRate(): number {
return binding.GetModelSampleRate(this._impl);
}
/**
* Enable decoding using an external scorer.
*
* @param aScorerPath The path to the external scorer file.
*
* @throws on error
*/
enableExternalScorer(aScorerPath: string): void {
const status = binding.EnableExternalScorer(this._impl, aScorerPath);
if (status !== 0) {
throw `EnableExternalScorer failed: ${binding.ErrorCodeToErrorMessage(status)} (0x${status.toString(16)})`;
}
}
/**
* Disable decoding using an external scorer.
*
* @throws on error
*/
disableExternalScorer(): void {
const status = binding.DisableExternalScorer(this._impl);
if (status !== 0) {
throw `DisableExternalScorer failed: ${binding.ErrorCodeToErrorMessage(status)} (0x${status.toString(16)})`;
}
}
/**
* Set hyperparameters alpha and beta of the external scorer.
*
* @param aLMAlpha The alpha hyperparameter of the CTC decoder. Language Model weight.
* @param aLMBeta The beta hyperparameter of the CTC decoder. Word insertion weight.
*
* @throws on error
*/
setScorerAlphaBeta(aLMAlpha: number, aLMBeta: number): void {
const status = binding.SetScorerAlphaBeta(this._impl, aLMAlpha, aLMBeta);
if (status !== 0) {
throw `SetScorerAlphaBeta failed: ${binding.ErrorCodeToErrorMessage(status)} (0x${status.toString(16)})`;
}
}
/**
* Use the DeepSpeech model to perform Speech-To-Text.
*
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
*
* @return The STT result. Returns undefined on error.
*/
stt(aBuffer: Buffer): string {
return binding.SpeechToText(this._impl, aBuffer);
}
/**
* Use the DeepSpeech model to perform Speech-To-Text and output metadata
* about the results.
*
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
* @param aNumResults Maximum number of candidate transcripts to return. Returned list might be smaller than this.
* Default value is 1 if not specified.
*
* @return :js:func:`Metadata` object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information.
* The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
*/
sttWithMetadata(aBuffer: Buffer, aNumResults: number = 1): Metadata {
return binding.SpeechToTextWithMetadata(this._impl, aBuffer, aNumResults);
}
/**
* Create a new streaming inference state. One can then call :js:func:`Stream.feedAudioContent` and :js:func:`Stream.finishStream` on the returned stream object.
*
* @return a :js:func:`Stream` object that represents the streaming state.
*
* @throws on error
*/
createStream(): Stream {
const [status, ctx] = binding.CreateStream(this._impl);
if (status !== 0) {
throw `CreateStream failed: ${binding.ErrorCodeToErrorMessage(status)} (0x${status.toString(16)})`;
}
return new Stream(ctx);
}
}
/**
* Frees associated resources and destroys model object.
*
* @param model A model pointer returned by :js:func:`Model`
*
*/
export function FreeModel(model: Model): void {
binding.FreeModel(model._impl);
}
/**
* Free memory allocated for metadata information.
*
* @param metadata Object containing metadata as returned by :js:func:`Model.sttWithMetadata` or :js:func:`Stream.finishStreamWithMetadata`
*/
export function FreeMetadata(metadata: Metadata): void {
binding.FreeMetadata(metadata);
}
/**
* Destroy a streaming state without decoding the computed logits. This
* can be used if you no longer need the result of an ongoing streaming
* inference and don't want to perform a costly decode operation.
*
* @param stream A streaming state pointer returned by :js:func:`Model.createStream`.
*/
export function FreeStream(stream: Stream): void {
binding.FreeStream(stream._impl);
}
/**
* Returns the version of this library. The returned version is a semantic
* version (SemVer 2.0.0).
*/
export function Version(): string {
return binding.Version();
}

3
native_client/javascript/node-pre-gyp.d.ts vendored Normal file
View File

@ -0,0 +1,3 @@
declare module "node-pre-gyp" {
export function find(path: String): any;
}

3
native_client/javascript/package.json.in
View File

@ -41,7 +41,8 @@
"devDependencies": { "devDependencies": {
"electron": "^1.7.9", "electron": "^1.7.9",
"node-gyp": "4.x - 5.x", "node-gyp": "4.x - 5.x",
"typescript": "3.6.x", "typescript": "3.8.x",
"typedoc": "0.17.x",
"@types/argparse": "1.0.x", "@types/argparse": "1.0.x",
"@types/node": "13.9.x" "@types/node": "13.9.x"
}, },

10
native_client/javascript/tsconfig.json
View File

@ -9,10 +9,14 @@
"noImplicitThis": true, "noImplicitThis": true,
"strictFunctionTypes": true, "strictFunctionTypes": true,
"strictNullChecks": true, "strictNullChecks": true,
"forceConsistentCasingInFileNames": true "forceConsistentCasingInFileNames": true,
"alwaysStrict": true,
"declaration": true,
"stripInternal": true
}, },
"files": [ "files": [
"index.d.ts", "index.ts",
"client.ts" "client.ts",
"node-pre-gyp.d.ts"
] ]
} }

3
taskcluster/docs-requirements.txt
View File

@ -1,6 +1,7 @@
breathe==4.14.2 breathe==4.14.2
semver==2.8.1 semver==2.8.1
sphinx==2.4.4 sphinx==2.4.4
sphinx-js==2.8 #FIXME: switch back to upstream sphinx-js when https://github.com/mozilla/sphinx-js/pull/135 is merged or the issue is fixed otherwise
git+git://github.com/reuben/sphinx-js.git@a24775935443d21028ee4a7025a407c78030c4e7#egg=sphinx-js
sphinx-rtd-theme==0.4.3 sphinx-rtd-theme==0.4.3
pygments==2.6.1 pygments==2.6.1