Skip to content

Update audiogen export script #198

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
AhSinan wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update audiogen export script #198

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions kleidiai-examples/audiogen/install_requirements.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#
# SPDX-FileCopyrightText: Copyright 2025 Arm Limited and/or its affiliates <open-source-office@arm.com>
# SPDX-FileCopyrightText: Copyright 2025-2026 Arm Limited and/or its affiliates <open-source-office@arm.com>
#
# SPDX-License-Identifier: Apache-2.0
#
Expand All @@ -9,31 +9,31 @@
# Install individual packages
echo "Installing required packages for the Audiogen module..."

# ai-edge-torch
pip install ai-edge-torch==0.4.0 \
"tf-nightly>=2.19.0.dev20250208" \
"ai-edge-litert-nightly>=1.1.2.dev20250305" \
"ai-edge-quantizer-nightly>=0.0.1.dev20250208"
# LiteRT torch
pip install litert-torch==0.8.0 \
"ai-edge-litert==2.1.2" \
"ai-edge-quantizer==0.4.2"

# Stable audio tools
pip install "stable_audio_tools==0.0.19"


# Working out dependency issues, this combination of packages has been tested on different systems (Linux and MacOS).
pip install --no-deps "torch==2.6.0" \
"torchaudio==2.6.0" \
"torchvision==0.21.0" \
"protobuf==5.29.4" \
pip install --no-deps "torch==2.9.0" \
"torchaudio==2.9.0" \
"torchvision==0.24.0" \
"protobuf==5.29.6" \
"numpy==1.26.4" \

# Packages to convert via onnx
# Packages to convert via onnx
pip install --no-deps "onnx==1.18.0" \
"onnxsim==0.4.36" \
"onnx-ir==0.1.16" \
"onnx2tf==1.27.10" \
"onnxscript==0.6.2" \
"tensorflow==2.19.0" \
"tf_keras==2.19.0" \
"onnx-graphsurgeon==0.5.8" \
"ai_edge_litert" \
"sng4onnx==1.0.4"

echo "Finished installing required packages for AudioGen submodules conversion."
Expand Down
22 changes: 12 additions & 10 deletions kleidiai-examples/audiogen/scripts/export_dit_autoencoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,26 +1,28 @@
#
# SPDX-FileCopyrightText: Copyright 2025 Arm Limited and/or its affiliates <open-source-office@arm.com>
# SPDX-FileCopyrightText: Copyright 2025-2026 Arm Limited and/or its affiliates <open-source-office@arm.com>
#
# SPDX-License-Identifier: Apache-2.0
#

# Disable GPU to avoid any issues during export
import os
os.environ["CUDA_VISIBLE_DEVICES"] = ""

import argparse
import json
import logging
import os

import ai_edge_torch
import litert_torch
import torch

from einops import rearrange

from ai_edge_torch.generative.quantize import quant_recipe, quant_recipe_utils
from ai_edge_torch.quantize import quant_config
from litert_torch.generative.quantize import quant_recipe, quant_recipe_utils
from litert_torch.quantize import quant_config
from utils_load_model import load_model

import stable_audio_tools

os.environ["CUDA_VISIBLE_DEVICES"] = ""
torch.manual_seed(0)
DEVICE = torch.device("cpu")

Expand Down Expand Up @@ -157,7 +159,7 @@ def export_audiogen(args) -> None:
# Create the dynamic weights int8 quantization config
quant_config_audiogen_int8 = quant_config.QuantConfig(
generative_recipe=quant_recipe.GenerativeQuantRecipe(
default=quant_recipe_utils.create_layer_quant_int8_dynamic(),
default=quant_recipe_utils.create_layer_quant_dynamic(),
)
)

Expand All @@ -178,7 +180,7 @@ def rotary_emb_const(_):
dit_model.model.transformer.rotary_pos_emb.forward_from_seq_len = rotary_emb_const

# Export the DiT to LiteRT format
edge_model = ai_edge_torch.convert(
edge_model = litert_torch.convert(
dit_model, sample_args=None, sample_kwargs=dit_model_example_input, quant_config=quant_config_audiogen_int8
)
edge_model.export("./dit_model.tflite")
Expand All @@ -192,7 +194,7 @@ def rotary_emb_const(_):
autoencoder_decoder_example_input = get_autoencoder_decoder_example_input(dtype)

# Export the Encoder part of the AutoEncoder to LiteRT format
edge_model = ai_edge_torch.convert(
edge_model = litert_torch.convert(
autoencoder_decoder,
autoencoder_decoder_example_input,
)
Expand All @@ -209,7 +211,7 @@ def rotary_emb_const(_):
autoencoder_encoder_example_input = get_autoencoder_encoder_example_input(dtype)

# Export the AutoEncoder to LiteRT format
edge_model = ai_edge_torch.convert(
edge_model = litert_torch.convert(
autoencoder_encoder,
autoencoder_encoder_example_input,
)
Expand Down