voice-assistant
A simple toy demo of a local voice assistant with whisper and large language model.
linyiLYi/voice-assistant is ranked 10,691 with 1,324 stars.
linyiLYi/voice-assistant is ranked 10,691 among these 8 peers; aws-samples/bedrock-chat is ranked 10,688.
| Name | Rank | Metrics |
|---|---|---|
| shuyu-labs/AntSK | 10,677 |
|
| miurla/babyagi-ui | 10,684 |
|
| xun082/DocFlow | 10,685 |
|
| aws-samples/bedrock-chat | 10,688 |
|
| ik190/macos-chatgpt-overlay-bar | 10,694 |
|
| run-bigpig/jcp | 10,708 |
|
| Robitx/gp.nvim | 10,712 |
|
| Capsize-Games/airunner | 10,714 |
|
| Parameter | Value |
|---|---|
| Language | Python |
| Category | Applications |
| Subcategory | Personal |
| Keywords | LocalAI, Voice bots |
| Stars | 1,324 |
| Forks | 210 |
| Contributors | 4 |
| Created date | 2023-12-09 |
| Updated date | 2026-10-10 |
| Stars in 1 day | 0 |
| Stars in 7 days | 1 |
| Rank | 10,691 |
| Previous rank | 10,678 |
| Rank change | -13 |
| 7-day stars rank | 9,943 |
| Previous 7-day stars rank | 10,000 |
| 7-day stars rank change | 57 |
| Total stars rank | 8,955 |
| Previous total stars rank | 8,943 |
| Total stars rank change | -12 |
| Country | China |
The voice recognition part of this project is from the Apple MLX example repo, and the textual responses are generated using the Yi model from 01. For more details, see the Acknowledgments section. File Structure This project is a single-script project, with main. is a simple script to view the microphone list, used in to specify the microphone number. is from the Apple MLX example repo, used for recognizing user's voice input. Installation Guide This project is based on
the Python programming language, and the Python version used for program operation is 3. It is recommended to configure the Python environment using Anaconda. The following setup process has been tested and passed on macOS systems. Windows and Linux can use speech_recognition and pyttsx3 to replace the whisper and say commands mentioned below. The following are console/terminal/shell commands. Environment Configuration Model Files The model files are stored in the folder and specified in the script via the
variable. It is recommended to download the gguf format models from TheBloke and XeIaso, where the 6B model has a smaller memory footprint: TheBloke/Yi-34B-Chat-GGUF XeIaso/Yi-6B-Chat-GGUF The voice recognition model is by default stored in , specified in the script via . The version converted by mlx-community can be directly downloaded. Model Files The voice recognition part of this project is based on OpenAI's whisper model, its implementation comes from the Apple MLX example
repo. The version used in this project is from January 2024, #80d1867. In the future, users can fetch new versions as needed. The responses in this project are generated by the large language model Yi from 01. The 8-bit quantized version made by TheBloke has a memory footprint of 39. 04 GB and is recommended for use if hardware conditions permit. This model runs locally based on the LangChain framework and llama. Thank you to all selfless programmers for
their contributions to the open-source community!
How many stars and forks are recorded?
linyiLYi/voice-assistant has 1,324 stars and 210 forks.
What is the repository rank?
linyiLYi/voice-assistant is ranked 10,691.
What language and category are recorded?
linyiLYi/voice-assistant has 1,324 stars, uses Python and belongs to Applications.
Which repository is closest in rank?
linyiLYi/voice-assistant is compared with aws-samples/bedrock-chat, ranked 10,688 with 1,324 stars.