Gigaam V2 Onnx

🚀 GigaAM v2 ONNX Models

GigaAM v2 models have been converted to ONNX format for onnx-asr. This project enables efficient automatic speech recognition using these converted models.

🚀 Quick Start

📦 Installation

First, install the onnx-asr library with the necessary dependencies:

pip install onnx-asr[cpu,hub]

💻 Usage Examples

Basic Usage

Here are examples of loading different GigaAM v2 models and recognizing a WAV file:

Load GigaAM v2 CTC model and recognize wav file

import onnx_asr

model = onnx_asr.load_model("gigaam-v2-ctc")
print(model.recognize("test.wav"))

Load GigaAM v2 RNN - T model and recognize wav file

import onnx_asr

model = onnx_asr.load_model("gigaam-v2-rnnt")
print(model.recognize("test.wav"))

Advanced Usage

Here is the code for exporting the models to ONNX format:

import gigaam
from pathlib import Path

onnx_dir = "gigaam-onnx"
model_type = "rnnt"  # or "ctc"

model = gigaam.load_model(
    model_type,
    fp16_encoder=False,  # only fp32 tensors
    use_flash=False,  # disable flash attention
)
model.to_onnx(dir_path=onnx_dir)

with Path(onnx_dir, "v2_vocab.txt").open("wt") as f:
    for i, token in enumerate(["\u2581", *(chr(ord("а") + i) for i in range(32)), "<blk>"]):
        f.write(f"{token} {i}\n")

📄 License

This project is licensed under the MIT license.