FCPE

.gitattributes

@@ -33,3 +33,7 @@ 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
+releases/v0.0.1/torchfcpe-0.0.1-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+releases/v0.0.2/torchfcpe-0.0.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+releases/v0.0.3/torchfcpe-0.0.3-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+releases/v0.0.4/torchfcpe-0.0.4-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

FCPE.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f28c2ccc865f87299d323df2fa390ec2112d91ba72c439de8b3be5235016f2
+size 82134543

README.md

@@ -0,0 +1,133 @@
+<h1 align="center">TorchFCPE</h1>
+
+## Overview
+
+TorchFCPE(Fast Context-based Pitch Estimation) is a PyTorch-based library designed for audio pitch extraction and MIDI conversion. This README provides a quick guide on how to use the library for audio pitch inference and MIDI extraction. 
+
+Note: that the MIDI extractor of FCPE is quantized from f0 using non neural network methods
+
+Note: I won't be updating FCPE (or benchmark) so soon, but I will definitely release a version with cleaned-up code by no later than next year.
+
+## Installation
+
+Before using the library, make sure you have the necessary dependencies installed:
+
+```bash
+pip install torchfcpe
+```
+
+## Usage
+
+### 1. Audio Pitch Inference
+
+```python
+from torchfcpe import spawn_bundled_infer_model
+import torch
+import librosa
+
+# Configure device and target hop size
+device = 'cpu'  # or 'cuda' if using a GPU
+sr = 16000  # Sample rate
+hop_size = 160  # Hop size for processing
+
+# Load and preprocess audio
+audio, sr = librosa.load('test.wav', sr=sr)
+audio = librosa.to_mono(audio)
+audio_length = len(audio)
+f0_target_length = (audio_length // hop_size) + 1
+audio = torch.from_numpy(audio).float().unsqueeze(0).unsqueeze(-1).to(device)
+
+# Load the model
+model = spawn_bundled_infer_model(device=device)
+
+# Perform pitch inference
+f0 = model.infer(
+    audio,
+    sr=sr,
+    decoder_mode='local_argmax',  # Recommended mode
+    threshold=0.006,  # Threshold for V/UV decision
+    f0_min=80,  # Minimum pitch
+    f0_max=880,  # Maximum pitch
+    interp_uv=False,  # Interpolate unvoiced frames
+    output_interp_target_length=f0_target_length,  # Interpolate to target length
+)
+
+print(f0)
+```
+
+### 2. MIDI Extraction
+
+```python
+# Extract MIDI from audio
+midi = model.extact_midi(
+    audio,
+    sr=sr,
+    decoder_mode='local_argmax',  # Recommended mode
+    threshold=0.006,  # Threshold for V/UV decision
+    f0_min=80,  # Minimum pitch
+    f0_max=880,  # Maximum pitch
+    output_path="test.mid",  # Save MIDI to file
+)
+
+print(midi)
+```
+
+### Notes
+
+- **Inference Parameters:**
+
+  - `audio`: Input audio as a `torch.Tensor`.
+  - `sr`: Sample rate of the audio.
+  - `decoder_mode` (Optional): Mode for decoding, 'local_argmax' is recommended.
+  - `threshold` (Optional): Threshold for voice/unvoiced decision; default is 0.006.
+  - `f0_min` (Optional): Minimum pitch value; default is 80 Hz.
+  - `f0_max` (Optional): Maximum pitch value; default is 880 Hz.
+  - `interp_uv` (Optional): Whether to interpolate unvoiced frames; default is False.
+  - `output_interp_target_length` (Optional): Length to which the output pitch should be interpolated.
+
+- **MIDI Extraction Parameters:**
+  - `audio`: Input audio as a `torch.Tensor`.
+  - `sr`: Sample rate of the audio.
+  - `decoder_mode` (Optional): Mode for decoding; 'local_argmax' is recommended.
+  - `threshold` (Optional): Threshold for voice/unvoiced decision; default is 0.006.
+  - `f0_min` (Optional): Minimum pitch value; default is 80 Hz.
+  - `f0_max` (Optional): Maximum pitch value; default is 880 Hz.
+  - `output_path` (Optional): File path to save the MIDI file. If not provided, only returns the MIDI structure.
+  - `tempo` (Optional): BPM for the MIDI file. If None, BPM is automatically predicted.
+
+## Additional Features
+
+- **Model as a PyTorch Module:**
+  You can use the model as a standard PyTorch module. For example:
+
+  ```python
+  # Change device
+  model = model.to(device)
+
+  # Compile model
+  model = torch.compile(model)
+  ```
+
+## Paper
+
+If you find our work useful, please consider citing the paper:
+
+```
+@misc{luo2025fcpefastcontextbasedpitch,
+      title={FCPE: A Fast Context-based Pitch Estimation Model}, 
+      author={Yuxin Luo and Ruoyi Zhang and Lu-Chuan Liu and Tianyu Li and Hangyu Liu},
+      year={2025},
+      eprint={2509.15140},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2509.15140}, 
+}
+```
+
+### Important details
+
+The model we use in our paper is DDSP-200K, you can get the model from here: [DDSP-200K Model](https://huggingface.co/ChiTu/FCPE/tree/main).
+
+And there's another model which released earlier, you can get it from here [FCPE-Previous](/torchfcpe/assets/fcpe_c_v001.pt).
+
+More information about experiments will be released after the paper is accepted or rejected.

model/.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

model/DDSP_200k.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8544427eebbf2baef6213cc9a05057e46961617a8e5bd96975a0d42da6a09059
+size 43362881

model/README.md

@@ -0,0 +1,3 @@
+---
+license: cc-by-nc-sa-4.0
+---

releases/v0.0.1/FCPE-0.0.1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924520da854e1c4c2ca44309c81b48e5ed219cb1616a3821b3ad1f452957d332
+size 40236269

releases/v0.0.1/torchfcpe-0.0.1-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9908abf3929e049e460f9d53f9108cb433249126de92039e3d74ade64473cba7
+size 40219623

releases/v0.0.2/FCPE-0.0.2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44bb35cacafe4c66ff174cd150f5f9202f9262e22d79faae5afc82fbe4d644b4
+size 40236537

releases/v0.0.2/torchfcpe-0.0.2-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d188dec17423cf483c4eb435ff721dc7573b82c959d6af6b552cd36332d5a875
+size 40219715

releases/v0.0.3/FCPE-0.0.3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5bb0fb924c81efcb4722852b3e5d45df034ae15ebda8a7c5f934d2abbc8a93
+size 40238649

releases/v0.0.3/torchfcpe-0.0.3-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92c2a3316b7dd71c24f8edfccc063bc0f1413b8ba3f9e556be9613db4d24fc1
+size 40220171

releases/v0.0.4/FCPE-0.0.4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df5af09d467bf3eacc0ddb19dea055fd7695fa3c2c093b4d0cafd7a4562f896
+size 40240639

releases/v0.0.4/torchfcpe-0.0.4-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f042c463d850d76c6f4899a0b84f0b694bb560adf05f4de951097a756d17472d
+size 40222012