Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/audio_mixed_noise_ref-voice1_onnx_fp16.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/audio_mixed_noise_ref-voice2_onnx_fp16.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/audio_mixed_noise_ref-voice3_onnx_fp16.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/audio_mixed_raw_ref-voice1_onnx_fp16.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/audio_mixed_raw_ref-voice2_onnx_fp16.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/audio_mixed_raw_ref-voice3_onnx_fp16.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/mixed_noise.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/mixed_raw.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/ref-voice1.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/ref-voice2.wav filter=lfs diff=lfs merge=lfs -text
+evaluation_wavs/ref-voice3.wav filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that you changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if distributed along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of title, non-infringement, merchantability, or fitness for a
+      particular purpose. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

README.md

@@ -0,0 +1,113 @@
+---
+license: apache-2.0
+tags:
+- target-speaker-extraction
+- speech-enhancement
+- audio-processing
+- onnx
+- onnxruntime
+- flow-matching
+- udit
+- t-predictor
+---
+
+# ONNX Target Speaker Extraction (TSE) Models
+
+This repository contains the ONNX-optimized versions of **MeanFlowTSE (UDiT)** and **T-Predictor** models used in the Target Speaker Extraction (TSE) application. The models are exported from PyTorch Lightning checkpoints and optimized for GPU (CUDA) and CPU deployment using ONNX Runtime.
+
+---
+
+## 1. Model Summary & Purpose
+
+These models work cooperatively to extract a target speaker's voice from a noisy mixture audio:
+
+1. **T-Predictor** (62.3 MB PyTorch -> 31.8 MB FP16 ONNX): Estimates the flow matching scaling factor ($\alpha$) by analyzing the reference target speaker voice and the mixed audio.
+2. **MeanFlowTSE (UDiT)** (1.37 GB PyTorch -> 688 MB FP16 ONNX): A large Diffusion-based velocity predictor model that iteratively reconstructs clean audio features under the guide of the predicted $\alpha$.
+
+---
+
+## 2. File Specifications & Download List
+
+* **Float32 Models** (Best compatibility & fidelity):
+  * `meanflow_tse_fp32.onnx` (1375.6 MB)
+  * `t_predictor_fp32.onnx` (63.4 MB)
+* **Float16 Models** (Highly recommended for GPU):
+  * `meanflow_tse_fp16.onnx` (688.2 MB)
+  * `t_predictor_fp16.onnx` (31.8 MB)
+* **Int8 Quantized Models** (Highly optimized for CPU):
+  * `meanflow_tse_int8.onnx` (345.8 MB)
+  * `t_predictor_int8.onnx` (16.4 MB)
+
+All evaluation-related source audio waveforms and reconstructed samples are available under the `evaluation_wavs/` directory.
+
+---
+
+## 3. Evaluation & Performance Benchmarks
+
+The benchmarks below were measured on an **NVIDIA GeForce GPU** with CUDA 12.1 and `onnxruntime-gpu` enabled. Numbers are averaged across 8 standard evaluation audio sets (combinations of target voices `ref-voice1` to `ref-voice4` and noisy mixtures `mixed_noise` and `mixed_raw`).
+
+| Model Format | Load Status | Avg Latency (ms) | Avg WAV MAE | Size Saving | Notes & Recommendations |
+| :--- | :--- | :--- | :--- | :--- | :--- |
+| **PyTorch (Baseline)** | **Success** | `761.1 ms` | *Baseline* | 0% (1.43 GB) | PyTorch lightning codebase dependency |
+| **ONNX FP32** | **Success** | **`692.8 ms`** | **`2.71e-05`** | 0% (1.43 GB) | **10% faster** than PyTorch, mathematically equivalent |
+| **ONNX FP16** | **Success** | **`676.3 ms`** | **`9.91e-03`** | **50% saving** | **Best for GPU**. Under 1% WAV difference, no audible noise |
+| **ONNX INT8** | **Success** | `6716.1 ms` | `2.62e-02` | **75% saving** | **Best for CPU** (AVX512/AMX). High latency on GPU due to CPU emulations |
+
+* **WAV MAE**: The Mean Absolute Error (MAE) calculated between PyTorch output waveforms and ONNX-reconstructed waveforms (range -1.0 to 1.0).
+* **FP16 Quality**: FP16 achieves an error rate under 1.0% compared to Float32, preserving high fidelity without introducing audible quantization noise, unlike INT8.
+
+---
+
+## 4. Key Fixes & Design Decisions
+
+### Timestep Embedder Type Mismatch Resolution
+During direct FP16 export, PyTorch's sinusoidal embedding inside `TimestepEmbedder` (`udit_meanflow.py`) hardcoded a `.float()` casting, leading to a type mismatch error when multiplied by float16 weights. We modified this behavior to dynamically cast the embeddings to match the MLP's weight precision:
+```python
+# Fixed code inside udit_meanflow.py
+t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+t_freq = t_freq.to(self.mlp[0].weight.dtype)  # Dynamic precision casting
+t_emb = self.mlp(t_freq)
+```
+This fix enables native FP16 execution in ONNX Runtime without loading issues.
+
+---
+
+## 5. How to Load and Run (Python Example)
+
+To run the models with CUDA acceleration:
+
+```python
+import onnxruntime as ort
+import numpy as np
+
+# Select CUDA Execution Provider
+providers = [('CUDAExecutionProvider', {'device_id': 0}), 'CPUExecutionProvider']
+
+# Load FP16 sessions
+tp_session = ort.InferenceSession("t_predictor_fp16.onnx", providers=providers)
+udit_session = ort.InferenceSession("meanflow_tse_fp16.onnx", providers=providers)
+
+# Example: T-Predictor Inference
+# Inputs: mixture (Batch, Time_Steps), enrollment (Batch, Time_Steps)
+mixture_data = np.random.randn(1, 48000).astype(np.float16)  # Use float16 for FP16 models
+enroll_data = np.random.randn(1, 48000).astype(np.float16)
+
+tp_inputs = {"mixture": mixture_data, "enrollment": enroll_data}
+tp_outputs = tp_session.run(None, tp_inputs)
+alpha = tp_outputs[0]
+print("Predicted Alpha:", alpha)
+```
+
+---
+
+## 6. Original Sources & Checkpoints
+* **Original Codebase**: MeanFlowTSE uses Diffusion-based Velocity Predictor architectures derived from DiT (Diffusion Transformers) and GLIDE concepts.
+  * UDiT Module reference: [GLIDE Text2Im](https://github.com/openai/glide-text2im)
+* **Checkpoint Origin**: The weights exported into these ONNX models were trained on clean-speech TSE datasets and extracted from the following local training checkpoints:
+  * MeanFlowTSE (UDiT) baseline: `backend/exp/best-clean-weights.ckpt`
+  * T-Predictor baseline: `backend/exp/t-predictor-clean-weights.ckpt`
+
+---
+
+## 7. License
+This repository is licensed under the Apache License 2.0. Feel free to use, modify, and distribute these models in your projects. Refer to the `LICENSE` file for details.

evaluation_wavs/audio_mixed_noise_ref-voice1_onnx_fp16.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2c24db983e31d02d753ecdbf6b90dc3dfff1d0624ffa071aeb66c8b2ffb30f
+size 501188

evaluation_wavs/audio_mixed_noise_ref-voice2_onnx_fp16.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72a401d1c26aecc8ae818a81bb48b6beaa915560492eb3b1b3850d52aa3ea5e
+size 501188

evaluation_wavs/audio_mixed_noise_ref-voice3_onnx_fp16.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdc0122c7f4a93d49b265d666d5a441a3650a86a5201a133a15bd915fb35732
+size 501188

evaluation_wavs/audio_mixed_raw_ref-voice1_onnx_fp16.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f380c66d4aee659d9288a358be0fecb8d15b951df4a0754e6bd5ea64d85d9b
+size 501188

evaluation_wavs/audio_mixed_raw_ref-voice2_onnx_fp16.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2e5157e5cedf6a61db7429a687f6c873288091293c3b479595ab93823daac6
+size 501188

evaluation_wavs/audio_mixed_raw_ref-voice3_onnx_fp16.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c2c29048ab3802ba85bb27a8a5af76b5d7a43571e7d2c092ce4c5e14737c42
+size 501188

evaluation_wavs/mixed_noise.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ba5e2a8ccd59bd94c59ae6f3c3ebd0e9c97aa6d3ed76f3204953700b4aadc8
+size 1381262

evaluation_wavs/mixed_raw.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbb23c40b7f325f0c7270c4ea80cb5205473abbf00b32291ca30dcdf0621650
+size 1381334

evaluation_wavs/ref-voice1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75159cfeba97900bfe9bedbb85a6e89e70d2b5d7e731deae43a4927938a2ad83
+size 148878

evaluation_wavs/ref-voice2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea391bbd8255a49ffb4fca71424163f1476cf2c030632022862a20ffa23d5d0
+size 340748

evaluation_wavs/ref-voice3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f75ec418ce3c2fdfc70f5501ecbde2f0872a0f8e0798fb0bf09e1ea953ed03d
+size 315954

meanflow_tse_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e53641e3e14a0f2e566e16b3015b6ee3e2dfc715e67c4d0990242e5b568424d
+size 688193018

meanflow_tse_fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00559ff2b2b88f7c15e02aeb0f23180c997fddcd7d340bb9108339820b1f38c8
+size 1375558425

meanflow_tse_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8853f7505255f2d3d6a5fc0796fd025cc5312e8eb8ef16dab8c75d9762c00d3c
+size 345831657

t_predictor_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68eca109b74ced769d8b113adc6f760f65ad57df8936f743b7484bc7e8cbc6df
+size 31787997

t_predictor_fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76bf0074675e6044a8e2a8d23ad91632228a594cfa4e7d8860d13c130804215
+size 63445669

t_predictor_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a47a7447d329b9f2f717967e62415b3f638dc869a00f6cfc89c2eb8f421667
+size 16416354