Mirror speechbrain/sepformer-wsj02mix

.gitattributes

@@ -0,0 +1,26 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+masknet.ckpt filter=lfs diff=lfs merge=lfs -text
+optimizer.ckpt filter=lfs diff=lfs merge=lfs -text
+brain.ckpt filter=lfs diff=lfs merge=lfs -text
+counter.ckpt filter=lfs diff=lfs merge=lfs -text
+decoder.ckpt filter=lfs diff=lfs merge=lfs -text
+encoder.ckpt filter=lfs diff=lfs merge=lfs -text
+lr_scheduler.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,123 @@
+---
+language: "en"
+thumbnail:
+tags:
+- Source Separation
+- Speech Separation
+- Audio Source Separation
+- WSJ02Mix
+- SepFormer
+- Transformer 
+- audio-to-audio 
+- audio-source-separation
+- speechbrain
+license: "apache-2.0"
+datasets:
+- WSJ0-2Mix
+metrics:
+- SI-SNRi
+- SDRi
+
+---
+
+<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
+<br/><br/>
+
+# SepFormer trained on WSJ0-2Mix
+
+This repository provides all the necessary tools to perform audio source separation with a [SepFormer](https://arxiv.org/abs/2010.13154v2) 
+model, implemented with SpeechBrain, and pretrained on WSJ0-2Mix dataset. For a better experience we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io). The model performance is 22.4 dB on the test set of WSJ0-2Mix dataset.
+
+| Release | Test-Set SI-SNRi | Test-Set SDRi |
+|:-------------:|:--------------:|:--------------:|
+| 09-03-21 | 22.4dB | 22.6dB |
+
+You can listen to example results obtained on the test set of WSJ0-2/3Mix through [here](https://sourceseparationresearch.com/static/sepformer_example_results/sepformer_results.html). 
+
+
+## Install SpeechBrain
+
+First of all, please install SpeechBrain with the following command:
+
+```
+pip install speechbrain
+```
+
+Please notice that we encourage you to read our tutorials and learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+### Perform source separation on your own audio file
+```python
+from speechbrain.inference.separation import SepformerSeparation as separator
+import torchaudio
+
+model = separator.from_hparams(source="speechbrain/sepformer-wsj02mix", savedir='pretrained_models/sepformer-wsj02mix')
+
+# for custom file, change path
+est_sources = model.separate_file(path='speechbrain/sepformer-wsj02mix/test_mixture.wav') 
+
+torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
+torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)
+```
+
+The system expects input recordings sampled at 8kHz (single channel).
+If your signal has a different sample rate, resample it (e.g, using torchaudio or sox) before using the interface.
+
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+### Training
+The model was trained with SpeechBrain (fc2eabb7).
+To train it from scratch follows these steps:
+1. Clone SpeechBrain:
+```bash
+git clone https://github.com/speechbrain/speechbrain/
+```
+2. Install it:
+```
+cd speechbrain
+pip install -r requirements.txt
+pip install -e .
+```
+
+3. Run Training:
+```
+cd  recipes/WSJ0Mix/separation
+python train.py hparams/sepformer.yaml --data_folder=your_data_folder
+```
+
+You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1cON-eqtKv_NYnJhaE9VjLT_e2ybn-O7u?usp=sharing).
+
+### Limitations
+The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
+
+#### Referencing SpeechBrain
+
+```bibtex
+@misc{speechbrain,
+  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
+  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
+  year={2021},
+  eprint={2106.04624},
+  archivePrefix={arXiv},
+  primaryClass={eess.AS},
+  note={arXiv:2106.04624}
+}
+```
+
+
+#### Referencing SepFormer
+```bibtex
+@inproceedings{subakan2021attention,
+      title={Attention is All You Need in Speech Separation}, 
+      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
+      year={2021},
+      booktitle={ICASSP 2021}
+}
+```
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/

brain.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e24193f36931b7f57932532efbdcf64971f42732383ba6808825f77db258f6
+size 28

config.json

@@ -0,0 +1,3 @@
+{
+  "speechbrain_interface": "SepformerSeparation"
+}

decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abea1a2d41151331b4c36071d1b3205aed940a189721f008b12a703e9c63e7e4
+size 17202

encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3139bb880b29ea77ae8a168b8f2ad6e8eb5c2c0904289676c223d0e93cd2a35d
+size 17267

hyperparams.yaml

@@ -0,0 +1,65 @@
+# ################################
+# Model: Inference for source separation with SepFormer
+# https://arxiv.org/abs/2010.13154
+# Generated from speechbrain/recipes/WSJ0Mix/separation/train/hparams/sepformer-wsj02mix.yaml
+# Dataset : wsj02mix
+# ###############################
+
+# Parameters
+sample_rate: 8000
+num_spks: 2
+
+# Specifying the network
+Encoder: !new:speechbrain.lobes.models.dual_path.Encoder
+  kernel_size: 16
+  out_channels: 256
+
+SBtfintra: !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+  num_layers: 8
+  d_model: 256
+  nhead: 8
+  d_ffn: 1024
+  dropout: 0
+  use_positional_encoding: true
+  norm_before: true
+
+SBtfinter: !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+  num_layers: 8
+  d_model: 256
+  nhead: 8
+  d_ffn: 1024
+  dropout: 0
+  use_positional_encoding: true
+  norm_before: true
+
+MaskNet: !new:speechbrain.lobes.models.dual_path.Dual_Path_Model
+  num_spks: !ref <num_spks>
+  in_channels: 256
+  out_channels: 256
+  num_layers: 2
+  K: 250
+  intra_model: !ref <SBtfintra>
+  inter_model: !ref <SBtfinter>
+  norm: ln
+  linear_layer_after_inter_intra: false
+  skip_around_intra: true
+
+Decoder: !new:speechbrain.lobes.models.dual_path.Decoder
+  in_channels: 256
+  out_channels: 1
+  kernel_size: 16
+  stride: 8
+  bias: false
+
+modules:
+  encoder: !ref <Encoder>
+  decoder: !ref <Decoder>
+  masknet: !ref <MaskNet>
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+  loadables:
+    masknet: !ref <MaskNet>
+    encoder: !ref <Encoder>
+    decoder: !ref <Decoder>
+
+

hyperparams_train.yaml

@@ -0,0 +1,163 @@
+# Generated 2021-02-26 from:
+# /scratch/csubakan/speechbrain_new/recipes/WSJ2Mix/separation/yamls/dptransformer78.yaml
+# yamllint disable
+# ################################
+# Model: SepFormer for source separation
+# https://arxiv.org/abs/2010.13154
+#
+# Dataset : WSJ0-mix
+# ################################
+# Basic parameters
+# Seed needs to be set at top of yaml, before objects with parameters are made
+#
+seed: 1234
+__set_seed: !apply:torch.manual_seed [1234]
+
+# Data params
+data_folder: /localscratch/csubakan.62709298.0/wsj0-mix/2speakers # wsj2mix or wsj3mix
+experiment_name: 78-speedchange-dynamicmix-hardcodegaussian
+output_folder: results/78-speedchange-dynamicmix-hardcodegaussian/1234
+train_log: results/78-speedchange-dynamicmix-hardcodegaussian/1234/train_log.txt
+save_folder: results/78-speedchange-dynamicmix-hardcodegaussian/1234/save
+train_data: results/78-speedchange-dynamicmix-hardcodegaussian/1234/save/wsj_tr.csv
+valid_data: results/78-speedchange-dynamicmix-hardcodegaussian/1234/save/wsj_cv.csv
+test_data: results/78-speedchange-dynamicmix-hardcodegaussian/1234/save/wsj_tt.csv
+wsj0_tr: /localscratch/csubakan.62709298.0/wsj0-processed/si_tr_s/
+
+# Experiment params
+auto_mix_prec: true
+test_only: false
+num_spks: 2 # set to 3 for wsj0-3mix
+progressbar: true
+save_audio: false # Save estimated sources on disk
+sample_rate: 8000
+
+# Training parameters
+N_epochs: 200
+batch_size: 1
+lr: 0.00015
+clip_grad_norm: 5
+loss_upper_lim: 999999  # this is the upper limit for an acceptable loss
+# if True, the training sequences are cut to a specified length
+limit_training_signal_len: false
+# this is the length of sequences if we choose to limit
+# the signal length of training sequences
+training_signal_len: 128000
+dynamic_mixing: regular
+
+# Augment parameters
+use_wavedrop: false
+use_speedperturb: true
+use_speedperturb_sameforeachsource: false
+use_rand_shift: false
+min_shift: -8000
+max_shift: 8000
+
+# Neural parameters
+N_encoder_out: 256
+out_channels: 256
+kernel_size: 16
+kernel_stride: 8
+
+threshold_byloss: true
+threshold: -30
+
+# Dataloader options
+dataloader_opts:
+  batch_size: 1
+  num_workers: 3
+
+speedperturb: !new:speechbrain.lobes.augment.TimeDomainSpecAugment
+  perturb_prob: 1.0
+  drop_freq_prob: 0.0
+  drop_chunk_prob: 0.0
+  sample_rate: 8000
+  speeds: [95, 100, 105]
+
+wavedrop: !new:speechbrain.lobes.augment.TimeDomainSpecAugment
+  perturb_prob: 0.0
+  drop_freq_prob: 1.0
+  drop_chunk_prob: 1.0
+  sample_rate: 8000
+
+
+Encoder: &id003 !new:speechbrain.lobes.models.dual_path.Encoder
+  kernel_size: 16
+  out_channels: 256
+
+
+SBtfintra: &id001 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+  num_layers: 8
+  d_model: 256
+  nhead: 8
+  d_ffn: 1024
+  dropout: 0
+  use_positional_encoding: true
+  norm_before: true
+
+SBtfinter: &id002 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+  num_layers: 8
+  d_model: 256
+  nhead: 8
+  d_ffn: 1024
+  dropout: 0
+  use_positional_encoding: true
+  norm_before: true
+
+MaskNet: &id005 !new:speechbrain.lobes.models.dual_path.Dual_Path_Model
+
+  num_spks: 2
+  in_channels: 256
+  out_channels: 256
+  num_layers: 2
+  K: 250
+  intra_model: *id001
+  inter_model: *id002
+  norm: ln
+  linear_layer_after_inter_intra: false
+  skip_around_intra: true
+
+Decoder: &id004 !new:speechbrain.lobes.models.dual_path.Decoder
+  in_channels: 256
+  out_channels: 1
+  kernel_size: 16
+  stride: 8
+  bias: false
+
+optimizer: !name:torch.optim.Adam
+  lr: 0.00015
+  weight_decay: 0
+
+loss: !name:speechbrain.nnet.losses.get_si_snr_with_pitwrapper
+
+lr_scheduler: &id007 !new:speechbrain.nnet.schedulers.ReduceLROnPlateau
+
+  factor: 0.5
+  patience: 4
+  dont_halve_until_epoch: 100
+
+epoch_counter: &id006 !new:speechbrain.utils.epoch_loop.EpochCounter
+  limit: 200
+
+modules:
+  encoder: *id003
+  decoder: *id004
+  masknet: *id005
+checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
+  checkpoints_dir: results/78-speedchange-dynamicmix-hardcodegaussian/1234/save
+  recoverables:
+    encoder: *id003
+    decoder: *id004
+    masknet: *id005
+    counter: *id006
+    lr_scheduler: *id007
+train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
+  save_file: results/78-speedchange-dynamicmix-hardcodegaussian/1234/train_log.txt
+
+
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        masknet: !ref <MaskNet>
+        encoder: !ref <Encoder>
+        decoder: !ref <Decoder>

masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57dd5f49bf21c5a2101bb4e46648d05d34d517a59e26f0b06646d0bebe8214c7
+size 113108458

test_mixture.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73235884251e3f575adc540597bc704363ffe50bd4fc5164e96bf0d7afd3a371
+size 66234