Espressif ESP-SR helps users build AI speech solutions.
ESP-SR framework includes the following modules:
These algorithms are provided in the form of a component, so they can be integrated into your projects with minimum effort.
[21/4/2025]: We add a new model WakeNet9s, which can run on chips that do not have PSRAM and do not support SIMD, such as ESP32C3 and ESP32C5. examples
[17/4/2025]: We add a new DOA(Direction of Arrival) algorithm.
[14/2/2025]: We release ESP-SR V2.0. Migration from ESP-SR V1.* to ESP-SR V2.*
[13/2/2025]: We release VADNet, a voice activaty detection model. You can use it to replace the WebRTC VAD and improve the performance.
Espressif wake word engine WakeNet is specially designed to provide a high performance and low memory footprint wake word detection algorithm for users, which enables devices always listen to wake words, such as “Alexa”, “Hi,lexin” and “Hi,ESP”. WakeNet9 and WakeNet9s models are supported. WakeNet9s is a cost-down version of WakeNet9, with fewer parameters and lower computational requirements.
Espressif offers two ways to customize the wake word, please refer to the following document to choose the one that meets your needs:
Espressif Speech Wake Words Customization Process or Training Wake Words by TTS sample.
The following wake words are supported in esp-sr:
wake words WakeNet9s WakeNet9 Hi,乐鑫 wn9s_hilexin wn9_hilexin Hi,ESP wn9s_hiesp wn9_hiesp 你好小智 wn9s_nihaoxiaozhi wn9_nihaoxiaozhi_tts Hi,Jason wn9s_hijason_tts2 wn9_hijason_tts2 你好喵伴 wn9_nihaomiaoban_tts2 小爱同学 wn9_xiaoaitongxue Hi,M Five wn9_himfive Alexa wn9_alexa Jarvis wn9_jarvis_tts Computer wn9_computer_tts Hey,Willow wn9_heywillow_tts Sophia wn9_sophia_tts Mycroft wn9_mycroft_tts Hey,Printer wn9_heyprinter_tts Hi,Joy wn9_hijoy_tts Hey,Wand wn9_heywanda_tts Astrolabe wn9_astrolabe_tts Hey,Ily wn9_heyily_tts2 Hi,Jolly wn9_hijolly_tts2 Hi,Fairy wn9_hifairy_tts2 Blue Chip wn9_bluechip_tts2 Hi,Wall E/Hi,瓦力 wn9_hiwalle_tts2 你好小鑫 wn9_nihaoxiaoxin_tts 小美同学 wn9_xiaomeitongxue_tts Hi,小星 wn9_hixiaoxing_tts 小龙小龙 wn9_xiaolongxiaolong_tts 喵喵同学 wn9_miaomiaotongxue_tts Hi,喵喵 wn9_himiaomiao_tts Hi,Lily/Hi,莉莉 wn9_hilili_tts Hi,Telly/Hi,泰力 wn9_hitelly_tts 小滨小滨/小冰小冰 wn9_xiaobinxiaobin_tts Hi,小巫 wn9_haixiaowu_tts 小鸭小鸭 wn9_xiaoyaxiaoya_tts2 璃奈板 wn9_linaiban_tts2 小酥肉 wn9_xiaosurou_tts2 小宇同学 wn9_xiaoyutongxue_tts2 小明同学 wn9_xiaomingtongxue_tts2 小康同学 wn9_xiaokangtongxue_tts2 小箭小箭 wn9_xiaojianxiaojian_tts2 小特小特 wn9_xiaotexiaote_tts2 你好小益 wn9_nihaoxiaoyi_tts2 你好百应 wn9_nihaobaiying_tts2 小鹿小鹿 wn9_xiaoluxiaolu_tts2 你好东东 wn9_nihaodongdong_tts2 你好小安 wn9_nihaoxiaoan_tts2NOTE: _tts suffix means this WakeNet model is trained by TTS samples. _tts2 suffix means this WakeNet model is trained by TTS Pipeline V2.
Espressif's speech command recognition model MultiNet is specially designed to provide a flexible off-line speech command recognition model. With this model, you can easily add your own speech commands, eliminating the need to train model again.
Currently, Espressif MultiNet supports up to 300 Chinese or English speech commands, such as “打开空调” (Turn on the air conditioner) and “打开卧室灯” (Turn on the bedroom light).
The following MultiNet models are supported in esp-sr:
language ESP32 ESP32-S3 ESP32-P4 Chinese mn2_cn mn5q8_cn, mn6_cn, mn7_cn mn7_cn English mn5q8_en, mn6_en, mn7_en mn7_en Supported Targets ESP32 ESP32-S3 ESP32-P4Espressif Audio Front-End AFE integrates AEC (Acoustic Echo Cancellation), VAD (Voice Activity Detection), BSS (Blind Source Separation) and NS (Noise Suppression), NSNET(Deep noise suppression) and other functions. It is designed to be used with the ESP-SR library.
Our two-mic Audio Front-End (AFE) have been qualified as a “Software Audio Front-End Solution” for Amazon Alexa Built-in devices.
Documentation and ResourcesESP-SR Documentation: ESP-SR Documentation
Migration Guide: Migration from V1.* to V2.*
Wake Word Training: Wake Word Training by TTS Pipeline V2.0
Examples: esp-skainet/examples
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4