SepFormer (code, models, paper, tools)

.gitattributes

@@ -33,3 +33,11 @@ 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
+An[[:space:]]Efficient[[:space:]]Speaker[[:space:]]Diarization[[:space:]]Pipeline[[:space:]]for[[:space:]]Conversational[[:space:]]Speech.pdf filter=lfs diff=lfs merge=lfs -text
+Attention[[:space:]]is[[:space:]]All[[:space:]]You[[:space:]]Need[[:space:]]in[[:space:]]Speech[[:space:]]Separation.pdf filter=lfs diff=lfs merge=lfs -text
+AV-SepFormer.[[:space:]]Cross-Attention[[:space:]]SepFormer[[:space:]]for[[:space:]]Audio-Visual[[:space:]]Target[[:space:]]Speaker[[:space:]]Extraction.pdf filter=lfs diff=lfs merge=lfs -text
+Dual-path[[:space:]]RNN.[[:space:]]Efficient[[:space:]]long[[:space:]]sequence[[:space:]]modeling[[:space:]]for[[:space:]]time-domain[[:space:]]single-channel[[:space:]]speech[[:space:]]separation.pdf filter=lfs diff=lfs merge=lfs -text
+models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/example_dns4-16k.wav filter=lfs diff=lfs merge=lfs -text
+models/Sepformer/de/sepformer_rescuespeech/example_rescuespeech16k.wav filter=lfs diff=lfs merge=lfs -text
+models/Sepformer/en/sepformer-whamr-enhancement/example_whamr.wav filter=lfs diff=lfs merge=lfs -text
+SepFormer.[[:space:]]Coarse-to-fine[[:space:]]Separator[[:space:]]Regression[[:space:]]Network[[:space:]]for[[:space:]]Table[[:space:]]Structure[[:space:]]Recognition.pdf filter=lfs diff=lfs merge=lfs -text

AV-SepFormer. Cross-Attention SepFormer for Audio-Visual Target Speaker Extraction.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc48943d188a9da9392dbe810fc1de2b3fe56c891eed621dd9572baf06944a64
+size 474358

An Efficient Speaker Diarization Pipeline for Conversational Speech.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5de3dd5af601cadc673dd42bba5178f23846dfbc7aca0b1e30d170fa91ede8
+size 823356

Attention is All You Need in Speech Separation.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ec5acd6458a965b79f511cb87a9b5bd317a7057b45bc0c51eb96e2bd3ca33f
+size 271339

Dual-path RNN. Efficient long sequence modeling for time-domain single-channel speech separation.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0922e9a32d0d781e11103b477c879a69b7690b408ef2032ae711276dd5eeb1
+size 322545

SepFormer. Coarse-to-fine Separator Regression Network for Table Structure Recognition.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fe6233c1909a9061565fe32e9e9996cfacadc5e268b2e7381a8127977e2a89
+size 16477595

code/AV-Sepformer.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bb563e66c495d5000ff7390abc83ff05290492510c6195b18023c496e93ade
+size 2607359

code/Separation-of-vocals-in-songs-based-on-sepformer.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc95fa4ec8b87e03a4f87431bafd2bdf154b4a247af8583757ec405063cdb8c
+size 93790

code/SeparationForKazakhSpeech.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3702bef31536be2b76f2e3d00c2ae870d935573de4aab24c906037d6feec19
+size 10157402

code/Sepformer.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb2a2dccbfe81108666dfbce9ff2bc22df3c24ab2de42abe305bfefe6709b2b
+size 7977839

code/SpeechSeparation.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082c00f26761812b0da192e69b6eabb4bb18dafebdd4bb483d3973c24ae1e857
+size 105214371

code/X-SepFormer.github.io.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72dc134d8d0c7d59a5f1ad9a74d23231644a90ed52d8b7fa92b97ea7791f0122
+size 44383489

code/mss-sepformer.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5777b26176f99f9d19fdc6f6e5045ec7a4ea5f2368f9234ad0088fb3f3f16816
+size 701807

code/sb_sepformer.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd051cdf945d16eb99ac12b856619e81555ff674d4f44463a2713b53faa4b35
+size 55281

code/sepformer-48k.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0096ee407cbeaca6b200b4a727b9917c81ecb1112fc8057919886607a43fec
+size 122754980

code/sepformer-tse.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13905e009d88354fcb21579e11f5dcebe3114eb2d238eab0fa4cc11f9cc237ea
+size 114198916

code/train-test-sepFormer.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c6d8346e1ceabb7a1d5469ca05f9878efb2d31332e2e373de6051d4632c370
+size 48661

models/AV-Sepformer/MuSE.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e6e10a80523133070e214fa7475333f29c65bc8cb8a82cc446b72dea8a01b8
+size 60355363

models/AV-Sepformer/av-convtasnet.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8621a009271a39e8b8a20e26a202527f45eddb7cd8a3ad28868a87d2e2503d04
+size 44310819

models/AV-Sepformer/av-sepformer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a036fb38dcb02c6ce49034ca537e9206290348ee21d4407c9fc38489132ba9b
+size 118763721

models/AV-Sepformer/source.txt

@@ -0,0 +1,2 @@
+https://github.com/lin9x/AV-Sepformer
+https://drive.google.com/drive/folders/1M26x5qCE0LuaEtZ76E_YSnW0hf_chGeq

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/.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/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/README.md

@@ -0,0 +1,136 @@
+---
+language:
+  - "en"
+  - "de"
+  - "ru"
+  - "fr"
+  - "it"
+  - "es"
+thumbnail:
+tags:
+- audio-to-audio 
+- Speech Enhancement
+- DNS-4
+- SepFormer
+- Transformer 
+- pytorch
+- speechbrain
+- Microsoft DNS Challenge
+- Deep Noise Suppression Challenge – ICASSP 2022
+license: "apache-2.0"
+datasets:
+- DNS-4
+metrics:
+- SI-SNR
+- PESQ
+- SIG
+- BAK
+- OVRL
+model-index:
+- name: sepformer-dns4-16k-enhancement
+  results:
+  - task:
+      name: Speech Enhancement
+      type: speech-enhancement
+    dataset:
+      name: DNS-4
+      type: deep-noise-suppression-challenge-icassp-2022
+      split: baseline-dev-set
+      args:
+        language: de
+    metrics:
+    - name: DNSMOS SIG
+      type: sig
+      value: '2.999'
+    - name: DNSMOS BAK
+      type: bak
+      value: '3.076'
+    - name: DNSMOS OVRL
+      type: ovrl
+      value: '2.437'
+---
+
+<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 Microsoft DNS-4 (Deep Noise Suppression Challenge 4 – ICASSP 2022) for speech enhancement (16k sampling frequency)
+This repository provides all the necessary tools to perform speech enhancement (denoising) with a [SepFormer](https://arxiv.org/abs/2010.13154v2) model, implemented with SpeechBrain. The model is trained on 1300HRS of Microsoft-DNS 4 dataset with 16k sampling frequency. For a better experience we encourage you to learn more about [SpeechBrain](https://speechbrain.github.io). Evaluation on DNS4 2022 baseline dev set using DNSMOS are-
+
+
+| Release | SIG | BAK | OVRL |
+|:-------------:|:--------------:|:--------------:|:--------------:|
+| 08-01-23 | 2.999 | 3.076 | 2.437 |
+
+DNSMOS - deep noise suppression (DNS)- mean opinion score (MOS) is a non-intrusive evaluation metric. It computes 3 scores– SIG (speech quality), BAK (background noise quality), and OVRL (overall quality) each on a scale of 1 to 5, with 5 being the best quality.
+
+## 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 speech enhancement on your own audio file
+
+```python
+from speechbrain.inference.separation import SepformerSeparation as separator
+import torchaudio
+
+model = separator.from_hparams(source="speechbrain/sepformer-dns4-16k-enhancement", savedir='pretrained_models/sepformer-dns4-16k-enhancement')
+
+# for custom file, change path
+est_sources = model.separate_file(path='speechbrain/sepformer-dns4-16k-enhancement/example_dns4-16k.wav') 
+
+torchaudio.save("enhanced_dns4-16k.wav", est_sources[:, :, 0].detach().cpu(), 16000)
+
+```
+
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+You can find our training results (models, logs, etc) [here](https://www.dropbox.com/sh/02c3wesc65402f6/AAApoxBApft-JwqHK-bddedBa?dl=0).
+
+### 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}
+}
+```
+
+### Referencing ICASSP 2022 Deep Noise Suppression Challenge
+```bibtex
+@inproceedings{dubey2022icassp,
+  title={ICASSP 2022 Deep Noise Suppression Challenge},
+  author={Dubey, Harishchandra and Gopal, Vishak and Cutler, Ross and Matusevych, Sergiy and Braun, Sebastian and Eskimez, Emre Sefik and Thakker, Manthan and Yoshioka, Takuya and Gamper, Hannes and Aichner, Robert},
+  booktitle={ICASSP},
+  year={2022}
+}
+```
+
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/config.json

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

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab10ab1aac337bbe77ad0cbdf75acb1fba952e2d34474d515de2f41ddfd9a24c
+size 17195

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33de46bbf0b55031f92346827723137478cf2f77204fd1360ba8833b5915e0ee
+size 17259

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/example_dns4-16k.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ca62a0abb72b896219a49fadd9ede1aa5a86610e35e352681a0b3aa0f20341
+size 256058

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/hyperparams.yaml

@@ -0,0 +1,67 @@
+# Generated 2023-02-21 from:
+# /netscratch/sagar/thesis/speechbrain/recipes/DNS/enhancement/hparams/resume-sepformer-dns_16k.yaml
+# yamllint disable
+# ################################
+# Model: SepFormer for source separation
+# https://arxiv.org/abs/2010.13154
+#
+# Author:  Sangeet Sagar 2022
+# Dataset : Microsoft-DNS
+# ################################
+
+# Basic parameters
+sample_rate: 16000
+num_spks: 1
+
+# Specifying the network
+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: 1
+  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
+
+modules:
+  encoder: *id003
+  decoder: *id004
+  masknet: *id005
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+  loadables:
+    encoder: !ref <Encoder>
+    masknet: !ref <MaskNet>
+    decoder: !ref <Decoder>

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfba4276bf051fc48b1d49350ef0612845328c1999cefb4c637fc02cdbabbbdd
+size 112839555

models/Sepformer/de,en,es,fr,it,ru/sepformer-dns4-16k-enhancement/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/speechbrain/sepformer-dns4-16k-enhancement

models/Sepformer/de/sepformer_rescuespeech/.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/Sepformer/de/sepformer_rescuespeech/README.md

@@ -0,0 +1,125 @@
+---
+language: "de"
+thumbnail:
+tags:
+- audio-to-audio 
+- Speech Enhancement
+- RescueSpeech
+- SepFormer
+- Transformer 
+- pytorch
+- speechbrain
+- Search and Rescue
+license: "apache-2.0"
+datasets:
+- RescueSpeech
+metrics:
+- SI-SNR
+- PESQ
+- SDR
+model-index:
+- name: rescuespeech_sepformer
+  results:
+  - task:
+      name: Speech Enhancement
+      type: speech-enhancement
+    metrics:
+    - name: Test PESQ
+      type: pesq
+      value: '2.24'
+    - name: Test SI-SNRi
+      type: si-snri
+      value: '7.849'
+    - name: Test SI-SDRi
+      type: si-sdri
+      value: '8.414'
+---
+
+<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 RescueSpeech for speech enhancement (16k sampling frequency)
+This repository provides all the necessary tools to perform speech enhancement (denoising) with a [SepFormer](https://arxiv.org/abs/2010.13154v2) model, implemented with SpeechBrain. The model was first trained on Microsoft-DNS 4 dataset and further fine-tuned on RescueSpeech dataset 16k sampling frequency. For a better experience we encourage you to learn more about [SpeechBrain](https://speechbrain.github.io). Given below is model performance on RescueSpeech test set.
+
+
+| Release | Test-Set SI-SNRi | Test-Set SI-SDRi |Test-Set PESQ |
+|:-------------:|:--------------:|:--------------:|:--------------:|
+| 07-01-23 | 7.849 | 8.414 | 2.24 |
+
+where SI-SNRi and SI-SDRi indicates the improvement in SI-SNR and SI-SDR metric.
+
+## 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 speech enhancement on your own audio file
+
+```python
+from speechbrain.inference.separation import SepformerSeparation as separator
+import torchaudio
+
+model = separator.from_hparams(source="speechbrain/rescuespeech_sepformer", savedir='pretrained_models/rescuespeech_sepformer')
+
+# for custom file, change path
+est_sources = model.separate_file(path='speechbrain/rescuespeech_sepformer/example_rescuespeech16k.wav') 
+
+torchaudio.save("enhanced_rescuespeech16k.wav", est_sources[:, :, 0].detach().cpu(), 16000)
+
+```
+
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+You can find our training results (models, logs, etc) [here](https://www.dropbox.com/sh/02c3wesc65402f6/AAApoxBApft-JwqHK-bddedBa?dl=0).
+
+### 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}
+}
+```
+
+### Referencing RescueSpeech
+```bibtex
+@misc{sagar2023rescuespeech,
+    title={RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain},
+    author={Sangeet Sagar and Mirco Ravanelli and Bernd Kiefer and Ivana Kruijff Korbayova and Josef van Genabith},
+    year={2023},
+    eprint={2306.04054},
+    archivePrefix={arXiv},
+    primaryClass={eess.AS}
+}
+```
+
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/

models/Sepformer/de/sepformer_rescuespeech/config.json

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

models/Sepformer/de/sepformer_rescuespeech/decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d272f965100f627a4a43d45dd919a7caf867372035139a91b8ece174c8b5f1
+size 17195

models/Sepformer/de/sepformer_rescuespeech/encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04882b82c623a27af12376cc05dc0eb6cc1d59fb483bfb463d89d7d6072ac4d
+size 17259

models/Sepformer/de/sepformer_rescuespeech/example_rescuespeech16k.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d804a2b9e506804ca9ee108e1cbe5634c8de9394ff2f41233856506ef44e39c
+size 445498

models/Sepformer/de/sepformer_rescuespeech/hyperparams.yaml

@@ -0,0 +1,68 @@
+
+# ################################
+# Model: SepFormer for source separation
+# https://arxiv.org/abs/2010.13154
+# Dataset : RescueSpeech
+# ################################
+
+sample_rate: 16000
+num_spks: 1
+
+# Encoder parameters
+N_encoder_out: 256
+out_channels: 256
+kernel_size: 16
+kernel_stride: 8
+
+# 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: 1
+  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:
+    encoder: !ref <Encoder>
+    masknet: !ref <MaskNet>
+    decoder: !ref <Decoder>

models/Sepformer/de/sepformer_rescuespeech/masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8fa1f883ca0d47cc825a69ca6bf8920f8325c6ac2efcf4e06bfa3c96d648c5
+size 112839555

models/Sepformer/de/sepformer_rescuespeech/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/speechbrain/sepformer_rescuespeech

models/Sepformer/en/sepformer-libri3mix/.gitattributes

@@ -0,0 +1,38 @@
+*.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
+*.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
+saved_model/**/* 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
+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
+masknet.ckpt filter=lfs diff=lfs merge=lfs -text

models/Sepformer/en/sepformer-libri3mix/README.md

@@ -0,0 +1,134 @@
+---
+language: "en"
+thumbnail:
+tags:
+- Source Separation
+- Speech Separation
+- Audio Source Separation
+- Libri3Mix
+- SepFormer
+- Transformer 
+- audio-to-audio 
+- audio-source-separation
+- speechbrain
+license: "apache-2.0"
+datasets:
+- Libri3Mix
+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 Libri3Mix
+
+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 Libri3Mix dataset. For a better experience we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io). The model performance is 19.8 dB SI-SNRi on the test set of Libri3Mix dataset.
+
+| Release | Test-Set SI-SNRi | Test-Set SDRi |
+|:-------------:|:--------------:|:--------------:|
+| 16-09-22 | 19.0dB | 19.4dB |
+
+
+## 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.pretrained import SepformerSeparation as separator
+import torchaudio
+
+model = separator.from_hparams(source="speechbrain/sepformer-libri3mix", savedir='pretrained_models/sepformer-libri3mix')
+
+est_sources = model.separate_file(path='speechbrain/sepformer-wsj03mix/test_mixture_3spks.wav') 
+
+torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
+torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)
+torchaudio.save("source3hat.wav", est_sources[:, :, 2].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/LibriMix/separation
+python train.py hparams/sepformer.yaml --data_folder=your_data_folder
+```
+Note: change num_spks to 3 in the yaml file.
+
+
+You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1DN49LtAs6cq1X0jZ8tRMlh2Pj6AecClz).
+
+### 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}
+}
+
+@article{subakan2023exploring,
+  author={Subakan, Cem and Ravanelli, Mirco and Cornell, Samuele and Grondin, François and Bronzi, Mirko},
+  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
+  title={Exploring Self-Attention Mechanisms for Speech Separation}, 
+  year={2023},
+  volume={31},
+  pages={2169-2180},
+
+```
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/

models/Sepformer/en/sepformer-libri3mix/config.json

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

models/Sepformer/en/sepformer-libri3mix/counter.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ada92f28b4ceda38562ebf047c6ff05400d4c572352a1142eedfef67d21e662
+size 2

models/Sepformer/en/sepformer-libri3mix/decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afdda4e4ecb9eefb5d49329193c7a9215ae7443aab206f2fe4eb0f50988ca53
+size 17272

models/Sepformer/en/sepformer-libri3mix/encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e949e80c1a96965b723460209bb155eac1fdb2f6d2cf4e7b3e1d3152716f38d0
+size 17272

models/Sepformer/en/sepformer-libri3mix/hyperparams.yaml

@@ -0,0 +1,68 @@
+# ################################
+# Model: Pretrained SepFormer for source separation
+# Dataset : Libri3Mix
+# ################################
+
+# Experiment params
+
+sample_rate: 8000
+num_spks: 3
+
+# Encoder parameters
+N_encoder_out: 256
+out_channels: 256
+kernel_size: 16
+kernel_stride: 8
+
+# 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: 3
+  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:
+     encoder: !ref <Encoder>
+     masknet: !ref <MaskNet>
+     decoder: !ref <Decoder>

models/Sepformer/en/sepformer-libri3mix/masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416af7b09d912c486261dd824788dd92d3b21373c8ec4d029209792522f4dbcb
+size 113375814

models/Sepformer/en/sepformer-libri3mix/optimizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2523adf0429ccfcca4ce95e87a5e62cbdac5a2240c11da40326272d8c4482bac
+size 206221049

models/Sepformer/en/sepformer-libri3mix/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/speechbrain/sepformer-libri3mix

models/Sepformer/en/sepformer-wham/.gitattributes

@@ -0,0 +1 @@
+*.ckpt filter=lfs diff=lfs merge=lfs -text