// Copyright 2020-2021 Alpha Cephei Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
/* This header contains the C API for Vosk speech recognition system */
#ifndef VOSK_API_H
#define VOSK_API_H
#ifdef __cplusplus
extern "C" {
#endif
/** Model stores all the data required for recognition
* it contains static data and can be shared across processing
* threads. */
typedef struct VoskModel VoskModel;
/** Speaker model is the same as model but contains the data
* for speaker identification. */
typedef struct VoskSpkModel VoskSpkModel;
/** Recognizer object is the main object which processes data.
* Each recognizer usually runs in own thread and takes audio as input.
* Once audio is processed recognizer returns JSON object as a string
* which represent decoded information - words, confidences, times, n-best lists,
* speaker information and so on */
typedef struct VoskRecognizer VoskRecognizer;
/**
* Batch model object
*/
typedef struct VoskBatchModel VoskBatchModel;
/**
* Batch recognizer object
*/
typedef struct VoskBatchRecognizer VoskBatchRecognizer;
/** Loads model data from the file and returns the model object
*
* @param model_path: the path of the model on the filesystem
* @returns model object or NULL if problem occured */
VoskModel *vosk_model_new(const char *model_path);
/** Releases the model memory
*
* The model object is reference-counted so if some recognizer
* depends on this model, model might still stay alive. When
* last recognizer is released, model will be released too. */
void vosk_model_free(VoskModel *model);
/** Check if a word can be recognized by the model
* @param word: the word
* @returns the word symbol if @param word exists inside the model
* or -1 otherwise.
* Reminding that word symbol 0 is for <epsilon> */
int vosk_model_find_word(VoskModel *model, const char *word);
/** Loads speaker model data from the file and returns the model object
*
* @param model_path: the path of the model on the filesystem
* @returns model object or NULL if problem occured */
VoskSpkModel *vosk_spk_model_new(const char *model_path);
/** Releases the model memory
*
* The model object is reference-counted so if some recognizer
* depends on this model, model might still stay alive. When
* last recognizer is released, model will be released too. */
void vosk_spk_model_free(VoskSpkModel *model);
/** Creates the recognizer object
*
* The recognizers process the speech and return text using shared model data
* @param model VoskModel containing static data for recognizer. Model can be
* shared across recognizers, even running in different threads.
* @param sample_rate The sample rate of the audio you going to feed into the recognizer.
* Make sure this rate matches the audio content, it is a common
* issue causing accuracy problems.
* @returns recognizer object or NULL if problem occured */
VoskRecognizer *vosk_recognizer_new(VoskModel *model, float sample_rate);
/** Creates the recognizer object with speaker recognition
*
* With the speaker recognition mode the recognizer not just recognize
* text but also return speaker vectors one can use for speaker identification
*
* @param model VoskModel containing static data for recognizer. Model can be
* shared across recognizers, even running in different threads.
* @param sample_rate The sample rate of the audio you going to feed into the recognizer.
* Make sure this rate matches the audio content, it is a common
* issue causing accuracy problems.
* @param spk_model speaker model for speaker identification
* @returns recognizer object or NULL if problem occured */
VoskRecognizer *vosk_recognizer_new_spk(VoskModel *model, float sample_rate, VoskSpkModel *spk_model);
/** Creates the recognizer object with the phrase list
*
* Sometimes when you want to improve recognition accuracy and when you don't need
* to recognize large vocabulary you can specify a list of phrases to recognize. This
* will improve recognizer speed and accuracy but might return [unk] if user said
* something different.
*
* Only recognizers with lookahead models support this type of quick configuration.
* Precompiled HCLG graph models are not supported.
*
* @param model VoskModel containing static data for recognizer. Model can be
* shared across recognizers, even running in different threads.
* @param sample_rate The sample rate of the audio you going to feed into the recognizer.
* Make sure this rate matches the audio content, it is a common
* issue causing accuracy problems.
* @param grammar The string with the list of phrases to recognize as JSON array of strings,
* for example "["one two three four five", "[unk]"]".
*
* @returns recognizer object or NULL if problem occured */
VoskRecognizer *vosk_recognizer_new_grm(VoskModel *model, float sample_rate, const char *grammar);
/** Adds speaker model to already initialized recognizer
*
* Can add speaker recognition model to already created recognizer. Helps to initialize
* speaker recognition for grammar-based recognizer.
*
* @param spk_model Speaker recognition model */
void vosk_recognizer_set_spk_model(VoskRecognizer *recognizer, VoskSpkModel *spk_model);
/** Configures recognizer to output n-best results
*
* <pre>
* {
* "alternatives": [
* { "text": "one two three four five", "confidence": 0.97 },
* { "text": "one two three for five", "confidence": 0.03 },
* ]
* }
* </pre>
*
* @param max_alternatives - maximum alternatives to return from recognition results
*/
void vosk_recognizer_set_max_alternatives(VoskRecognizer *recognizer, int max_alternatives);
/** Enables words with times in the output
*
* <pre>
* "result" : [{
* "conf" : 1.000000,
* "end" : 1.110000,
* "start" : 0.870000,
* "word" : "what"
* }, {
* "conf" : 1.000000,
* "end" : 1.530000,
* "start" : 1.110000,
* "word" : "zero"
* }, {
* "conf" : 1.000000,
* "end" : 1.950000,
* "start" : 1.530000,
* "word" : "zero"
* }, {
* "conf" : 1.000000,
* "end" : 2.340000,
* "start" : 1.950000,
* "word" : "zero"
* }, {
* "conf" : 1.000000,
* "end" : 2.610000,
* "start" : 2.340000,
* "word" : "one"
* }],
* </pre>
*
* @param words - boolean value
*/
void vosk_recognizer_set_words(VoskRecognizer *recognizer, int words);
/** Like above return words and confidences in partial results
*
* @param partial_words - boolean value
*/
void vosk_recognizer_set_partial_words(VoskRecognizer *recognizer, int partial_words);
/** Set NLSML output
* @param nlsml - boolean value
*/
void vosk_recognizer_set_nlsml(VoskRecognizer *recognizer, int nlsml);
/** Accept voice data
*
* accept and process new chunk of voice data
*
* @param data - audio data in PCM 16-bit mono format
* @param length - length of the audio data
* @returns 1 if silence is occured and you can retrieve a new utterance with result method
* 0 if decoding continues
* -1 if exception occured */
int vosk_recognizer_accept_waveform(VoskRecognizer *recognizer, const char *data, int length);
/** Sa
没有合适的资源?快使用搜索试试~ 我知道了~
编译供c语言使用的Vosk库,可以直接使用省去编译的麻烦过程
共6个文件
dll:4个
h:1个
lib:1个
4 下载量 185 浏览量
2024-11-07
21:27:10
上传
评论
收藏 12.49MB ZIP 举报
温馨提示
Vosk是一个开源的语音识别工具,支持中英文及多种语言,具备离线识别能力,且不依赖互联网。优势 Vosk 是一个离线开源语音识别工具包,它的优点在于: 轻量:Vosk 提供轻量级的模型(小于 50MB 大小),可以用于低功耗平台(例如 Android、树莓派之类) 多编程语言、多平台支持:Python、Java、Node.js、C#、C++、Rust、Go 等 多语种支持:支持二十多种语言的识别(包括中文) 实时性:实时性语音识别场景下,vosk 的延迟非常低 简单来讲,你电脑中有 Python 环境,再下载一个 50 MB 的模型,就可以用 Vosk 实现一个正确率还可以接受的语言识别相关的项目。而像 Whisper 虽然识别效果好,但是对硬件要求很高,同时部署起来麻烦(例如需要配置 CUDA 环境),另外也不是很适用于实时性场景。 此包为编译好的c调用的运行库,有需要的可以直接下载使用。
资源推荐
资源详情
资源评论
收起资源包目录
vosk-win64-0.3.42.zip (6个子文件)
vosk-win64-0.3.42
libgcc_s_seh-1.dll 1.21MB
libvosk.lib 15.8MB
libvosk.dll 24.79MB
libwinpthread-1.dll 578KB
libstdc++-6.dll 18.54MB
vosk_api.h 12KB
共 6 条
- 1
资源评论
我喜欢就喜欢
- 粉丝: 279
- 资源: 56
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 模拟题最终版.docx
- Java Web实验报告一:通讯录
- 不同温度下的光谱数据,仅截取550nm-700nm
- 不同温度下的光谱数据,仅截取550nm-700nm
- HengCe-18900-2024-2030全球与中国eMMC和UFS市场现状及未来发展趋势-样本.docx
- 2024第十四届APMCM亚太地区-C题完整论文.pdf
- HengCe-18900-2024-2030中国硬碳负极材料市场现状研究分析与发展前景预测报告-样本.docx
- PHP面向对象与设计模式
- HengCe-2024-2030全球与中国掩模基板市场现状及未来发展趋势-样本
- CSS3制作的聚光灯下倒影文字选装动画特效代码.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功