EZ-VC (code, models, paper)

.gitattributes

@@ -33,3 +33,4 @@ 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
+EZ-VC.[[:space:]]Easy[[:space:]]Zero-shot[[:space:]]Any-to-Any[[:space:]]Voice[[:space:]]Conversion.pdf filter=lfs diff=lfs merge=lfs -text

EZ-VC. Easy Zero-shot Any-to-Any Voice Conversion.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c3c80fc2ebae83ba951e977c9b1c1d5e2b8f8354906c08bc180d94000de418
+size 634859

code/EZ-VC.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a63d75c060671d91e0180b786d80cf7a799a496cd72d516ec330496f66183b
+size 4492684

code/EZ_VC (dvrk-dvys) streaming + diarization.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad38807f825bcd707cbc0d462414c5a4eec500b9490b9262c945cbd958fd4f00
+size 108436510

models/EZ-VC/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

models/EZ-VC/README.md

@@ -0,0 +1,87 @@
+---
+license: cc-by-nc-4.0
+pipeline_tag: audio-to-audio
+library_name: f5-tts
+extra_gated_prompt: "You agree to not use the model to generate, share, or promote content that is illegal, harmful, deceptive, or intended to impersonate real individuals without their informed consent."
+extra_gated_fields:
+  Affiliation: text
+  Country: country
+I agree to use this model for non-commercial use ONLY: checkbox
+---
+
+# EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion
+
+[![github](https://img.shields.io/badge/Github-code-brightgreen)](https://github.com/EZ-VC/EZ-VC)
+[![arXiv](https://img.shields.io/badge/EMNLP-findings.2025.1077-b31b1b.svg?logo=acl)](https://aclanthology.org/2025.findings-emnlp.1077/)
+[![demo](https://img.shields.io/badge/Demo-page-yellow.svg)](https://ez-vc.github.io/EZ-VC-Demo/)
+[![lab](https://img.shields.io/badge/SPRING-Lab-purple)](https://asr.iitm.ac.in/)
+<!-- <img src="https://github.com/user-attachments/assets/12d7749c-071a-427c-81bf-b87b91def670" alt="Watermark" style="width: 40px; height: auto"> -->
+
+
+### Our paper has been published in the Findings of EMNLP 2025!
+
+## Installation
+
+### Create a separate environment if needed
+
+```bash
+# Create a python 3.10 conda env (you could also use virtualenv)
+conda create -n ez-vc python=3.10
+conda activate ez-vc
+```
+
+### Local installation
+
+```bash
+git clone https://github.com/EZ-VC/EZ-VC
+cd EZ-VC
+git submodule update --init --recursive
+pip install -e .
+
+# Install espnet for xeus (Exactly this version)
+pip install 'espnet @ git+https://github.com/wanchichen/espnet.git@ssl'
+```
+
+## Inference
+
+We have provided a Jupyter notebook for inference in "src/f5_tts/infer/infer.ipynb".
+
+Open [Inference notebook](https://github.com/EZ-VC/EZ-VC/blob/main/src/f5_tts/infer/infer.ipynb).
+
+Run all. 
+
+The converted audio will be available at the last cell.
+
+
+## Acknowledgements
+
+- [F5-TTS](https://arxiv.org/abs/2410.06885) for opensourcing their code which has made EZ-VC possible.
+
+## Citation
+If our work and codebase is useful for you, please cite as:
+```
+@inproceedings{joglekar-etal-2025-ez,
+    title = "{EZ}-{VC}: Easy Zero-shot Any-to-Any Voice Conversion",
+    author = "Joglekar, Advait  and
+      Singh, Divyanshu  and
+      Bhatia, Rooshil Rohit  and
+      Umesh, Srinivasan",
+    editor = "Christodoulopoulos, Christos  and
+      Chakraborty, Tanmoy  and
+      Rose, Carolyn  and
+      Peng, Violet",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
+    month = nov,
+    year = "2025",
+    address = "Suzhou, China",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.findings-emnlp.1077/",
+    doi = "10.18653/v1/2025.findings-emnlp.1077",
+    pages = "19768--19774",
+    ISBN = "979-8-89176-335-7",
+    abstract = "Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual settings. They are also often unable to generalize for speakers of unseen languages and accents. In this paper, we adopt a simple yet effective approach that combines discrete speech representations from self-supervised models with a non-autoregressive Diffusion-Transformer based conditional flow matching speech decoder. We show that this architecture allows us to train a voice-conversion model in a purely textless, self-supervised fashion. Our technique works without requiring multiple encoders to disentangle speech features. Our model also manages to excel in zero-shot cross-lingual settings even for unseen languages. We provide our code, model checkpoint and demo samples here: https://github.com/ez-vc/ez-vc"
+}
+```
+## License
+
+Our code is released under MIT License. The pre-trained models are licensed under the CC-BY-NC license. Sorry for any inconvenience this may cause.

models/EZ-VC/kmeans_xeus_500_multilingual.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb3a0f2282c06d2155d717d6ae582d0906c613fe2f7e7f6f4e62afed505dc86
+size 2050874

models/EZ-VC/model_2700000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87746af319d3de01d7672425f6c21ac3a5c00129c3b46d2f8007d2046d49f39
+size 1344003801

models/EZ-VC/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/SPRINGLab/EZ-VC

models/EZ-VC/vocab.txt

@@ -0,0 +1,501 @@
+ 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+