# Clone original GigaAM repo:
git clone https://github.com/salute-developers/GigaAM
cd GigaAM

# Create temp venv:
python -m venv ./tmp_venv
source ./tmp_venv/bin/activate

# Install project:
pip install -e .

Acquire chosen models:

import gigaam

onnx_dir = '/target/onnx/model/paths'
model_version = 'v3_ctc'  # Options: v3_* models

model = gigaam.load_model(model_version)
model.to_onnx(dir_path=onnx_dir)

Fetch SentencePieceProcessor tokenizer model

From a cache ~/.cache/gigaam/{model_name}_tokenizer.model
From a sberdevices server https://cdn.chatwm.opensmodel.sberdevices.ru/GigaAM/{model_name}_tokenizer.model

Then you may remove original project:

cd ..
rm -r ./GigaAM

Install this (gigaam-onnx) project
Set up onnx runtime and load chosen model:

import onnxruntime as ort
from gigaam_onnx import GigaAMV3E2ERNNT, GigaAMV3RNNT, GigaAMV3E2ECTC, GigaAMV3CTC
import numpy as np

# Set up ONNX runtime
if 'CUDAExecutionProvider' in ort.get_available_providers():
    provider = 'CUDAExecutionProvider'
else:
    provider = 'CPUExecutionProvider"
opts = ort.SessionOptions()
opts.intra_op_num_threads = 16
opts.execution_mode = ort.ExecutionMode.ORT_SEQUENTIAL
opts.log_severity_level = 3

e2e_rnnt_model = GigaAMV3E2ERNNT(
    '/path/to/onnx/files/v3_e2e_rnnt_decoder.onnx',
    '/path/to/onnx/files/v3_e2e_rnnt_encoder.onnx',
    '/path/to/onnx/files/v3_e2e_rnnt_joint.onnx',
    '/path/to/onnx/files/v3_e2e_rnnt_tokenizer.model',
    provider,
    opts
)

rnnt_model = GigaAMV3RNNT(
    '/path/to/onnx/files/v3_rnnt_decoder.onnx',
    '/path/to/onnx/files/v3_rnnt_encoder.onnx',
    '/path/to/onnx/files/v3_rnnt_joint.onnx',
    provider,
    opts
)

e2e_ctc_model = GigaAMV3E2ECTC(
    '/path/to/onnx/files/v3_e2e_ctc.onnx',
    '/path/to/onnx/files/v3_e2e_ctc_tokenizer.model',
    provider,
    opts
)

ctc_model = GigaAMV3CTC(
    '/path/to/onnx/files/v3_ctc.onnx',
    provider,
    opts
)

# Load wav 16kHz mono PCM
wav_data = ...
audio_array = np.array(wav_data)

# Single fragment transcribing with per-char timings 
text, timings = ctc_model.transcribe(audio_array)

# Batch transcribing with per-char timings
text, timings = e2e_ctc_model.transcribe_batch([audio_array])[0]

# Batch joined transcribing - joins fragments by lengts provided and returns continuous text with per-char timings
text, timings = e2e_rnnt_model.transcribe_batch(
    [audio_array]  # audio chunks
    [1]  # length of chunks to combine
)[0]