- Implement POST /audio/transcriptions and /v1/audio/transcriptions
endpoints for automatic speech recognition
- Add support for multipart/form-data audio file uploads
- Support multiple audio formats (wav, mp3, m4a, etc.)
- Implement language detection with 29 supported languages
- Return transcription text in OpenAI-compatible JSON format
- Add proper error handling and validation
- Include comprehensive tests for ASR functionality
refactor(api): restructure API modules and export MODEL
- Move API declarations to src/api/mod.rs
- Add ASR module and type definitions
- Export MODEL static for use in ASR module
- Mount ASR routes at both /audio and /v1/audio endpoints
Change --weight-path argument from required to optional in both serv and run
subcommands. When not specified, it defaults to ~/.aha/{model_id}. Add
get_default_weight_path function to handle the default path resolution.
Update help text to reflect the optional nature of the weight path parameter.
feat(cli): add direct model inference via new run subcommand
- Add `aha run` CLI subcommand for direct model inference without HTTP service
- Support multiple models including Qwen series, OCR models, ASR models, and voice generation
- Implement input/output handling with file path support and auto-generation
- Add comprehensive documentation in CLI_USAGE.md with examples
- Include performance timing for model loading and inference operations
- Add macOS build target to Makefile with Metal support
```
XiaoYang
Yijun Zhao