blob: 0aaefd1363b5010cdf68e953775797ec0d44cd4f (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|
//! # 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;
|
