diff options
| author | soryu <soryu@soryu.co> | 2025-12-21 01:27:02 +0000 |
|---|---|---|
| committer | soryu <soryu@soryu.co> | 2025-12-23 14:47:18 +0000 |
| commit | 3c696cfc9005e73be5ed46f8941dfc8f0aca7102 (patch) | |
| tree | 497bffd67001501a003739cfe0bb790502ffd50a /parakeet-rs/src/lib.rs | |
| parent | 55cacf6e1a087c0fa6950a1ddeb09060f787e541 (diff) | |
| download | soryu-3c696cfc9005e73be5ed46f8941dfc8f0aca7102.tar.gz soryu-3c696cfc9005e73be5ed46f8941dfc8f0aca7102.zip | |
Create container image and move parakeet fork to vendor dir
Diffstat (limited to 'parakeet-rs/src/lib.rs')
| -rw-r--r-- | parakeet-rs/src/lib.rs | 74 |
1 files changed, 0 insertions, 74 deletions
diff --git a/parakeet-rs/src/lib.rs b/parakeet-rs/src/lib.rs deleted file mode 100644 index 0aaefd1..0000000 --- a/parakeet-rs/src/lib.rs +++ /dev/null @@ -1,74 +0,0 @@ -//! # parakeet-rs -//! -//! Rust bindings for NVIDIA's Parakeet speech recognition model using ONNX Runtime. -//! -//! Parakeet is a state-of-the-art automatic speech recognition (ASR) model developed by NVIDIA, -//! based on the FastConformer-TDT architecture with 600 million parameters. -//! -//! ## Features -//! -//! - Easy-to-use API for speech-to-text transcription -//! - Support for ONNX format models -//! - 16kHz mono audio input -//! - Punctuation and capitalization included in output -//! - Fast inference using ONNX Runtime -//! -//! ## Quick Start -//! -//! ```ignore -//! use parakeet_rs::Parakeet; -//! -//! // Load the model -//! let parakeet = Parakeet::from_pretrained(".")?; -//! -//! // Transcribe audio file -//! let text = parakeet.transcribe_file("audio.wav")?; -//! println!("Transcription: {}", text); -//! ``` -//! -//! ## Model Requirements -//! -//! Your model directory should contain: -//! - `model.onnx` - The ONNX model file -//! - `model.onnx_data` - External model weights -//! - `config.json` - Model configuration -//! - `preprocessor_config.json` - Audio preprocessing configuration -//! - `tokenizer.json` - Tokenizer vocabulary -//! - `tokenizer_config.json` - Tokenizer configuration -//! -//! ## Audio Requirements -//! -//! - Format: WAV -//! - Sample Rate: 16kHz -//! - Channels: Mono (stereo will be converted automatically) -//! - Bit Depth: 16-bit PCM or 32-bit float - -mod audio; -mod config; -mod decoder; -mod decoder_tdt; -mod error; -mod execution; -mod model; -mod model_tdt; -mod parakeet; -mod parakeet_tdt; -mod timestamps; -mod vocab; -mod model_eou; -mod parakeet_eou; -#[cfg(feature = "sortformer")] -pub mod sortformer; - -pub use error::{Error, Result}; -pub use execution::{ExecutionProvider, ModelConfig as ExecutionConfig}; -pub use parakeet::Parakeet; -pub use parakeet_tdt::ParakeetTDT; -pub use timestamps::TimestampMode; - -pub use config::{ModelConfig as ModelConfigJson, PreprocessorConfig}; - -pub use decoder::{ParakeetDecoder, TimedToken, TranscriptionResult}; -pub use model::ParakeetModel; -pub use model_eou::ParakeetEOUModel; -pub use parakeet_eou::ParakeetEOU;
\ No newline at end of file |
