ECAPA-TDNN (models)

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 ECAPA-TDNN[[:space:]]based[[:space:]]online[[:space:]]discussion[[:space:]]activity-level[[:space:]]evaluation.pdf filter=lfs diff=lfs merge=lfs -text
 ECAPA-TDNN.[[:space:]]Emphasized[[:space:]]Channel[[:space:]]Attention,[[:space:]]Propagation[[:space:]]and[[:space:]]Aggregation[[:space:]]in[[:space:]]TDNN[[:space:]]Based[[:space:]]Speaker[[:space:]]Verification.pdf filter=lfs diff=lfs merge=lfs -text
 Validation[[:space:]]of[[:space:]]an[[:space:]]ECAPA-TDNN[[:space:]]system[[:space:]]for[[:space:]]Forensic[[:space:]]Automatic[[:space:]]Speaker[[:space:]]Recognition[[:space:]]under[[:space:]]case[[:space:]]work[[:space:]]conditions.pdf filter=lfs diff=lfs merge=lfs -text
+models/spkrec-ecapa-voxceleb/example1.wav filter=lfs diff=lfs merge=lfs -text

models/Hyper-ECAPA-TDNN/.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/Hyper-ECAPA-TDNN/README.md

@@ -0,0 +1,3 @@
+---
+license: apache-2.0
+---

models/Hyper-ECAPA-TDNN/model_0002.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85932ea3300c4a4ea6d3e07950bab36bcd7b17a149cd2af0606363aa89efe2c
+size 66659819

models/Hyper-ECAPA-TDNN/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Zroslav/Hyper-ECAPA-TDNN

models/VPR_zhvoice_EcapaTdnn/.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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/VPR_zhvoice_EcapaTdnn/README.md

@@ -0,0 +1,10 @@
+---
+license: gpl-3.0
+language:
+- zh
+pipeline_tag: audio-classification
+---
+# Voiceprint Recognition model of zhvoice based on EcapaTdnn
+This is a VPR model trained on [**zhvoice**](https://aistudio.baidu.com/aistudio/datasetdetail/133922) dataset using [**yeyupiaoling/VoiceprintRecognition-Pytorch**](https://github.com/yeyupiaoling/VoiceprintRecognition-Pytorch). I choosed MelSpectrogram as preprocessing method.
+
+You can use it with my [**2DIPW/audio_dataset_vpr**](https://github.com/2DIPW/audio_dataset_vpr) project (modified from yyupiaoling/VoiceprintRecognition-Pytorch), or the origin project.

models/VPR_zhvoice_EcapaTdnn/config.yml

@@ -0,0 +1,60 @@
+# 数据集参数
+dataset_conf:
+  # 训练的批量大小
+  batch_size: 64
+  # 说话人数量，即分类大小
+  num_speakers: 3242
+  # 读取数据的线程数量
+  num_workers: 4
+  # 过滤最短的音频长度
+  min_duration: 0.5
+  # 最长的音频长度，大于这个长度会裁剪掉
+  max_duration: 3
+  # 是否裁剪静音片段
+  do_vad: False
+  # 音频的采样率
+  sample_rate: 16000
+  # 是否对音频进行音量归一化
+  use_dB_normalization: True
+  # 对音频进行音量归一化的音量分贝值
+  target_dB: -20
+  # 训练数据的数据列表路径
+  train_list: 'dataset/train_list.txt'
+  # 测试数据的数据列表路径
+  test_list: 'dataset/test_list.txt'
+
+# 数据预处理参数
+preprocess_conf:
+  # 音频预处理方法，支持：MelSpectrogram、Spectrogram、MFCC
+  feature_method: 'MelSpectrogram'
+
+# MelSpectrogram的参数，其他的预处理方法查看对应API设设置参数
+feature_conf:
+  sample_rate: 16000
+  n_fft: 1024
+  hop_length: 320
+  win_length: 1024
+  f_min: 50.0
+  f_max: 14000.0
+  n_mels: 64
+
+optimizer_conf:
+  # 优化方法，支持Adam、AdamW、SGD
+  optimizer: 'Adam'
+  # 初始学习率的大小
+  learning_rate: 0.001
+  weight_decay: 1e-6
+
+model_conf:
+  # 所使用的池化层，支持ASP、SAP、TSP、TAP
+  pooling_type: 'ASP'
+
+train_conf:
+  # 训练的轮数
+  max_epoch: 30
+  log_interval: 100
+
+# 所使用的模型，支持EcapaTdnn、TDNN、Res2Net、ResNetSE
+use_model: 'EcapaTdnn'
+# 所使用的损失函数，支持AAMLoss、AMLoss、ARMLoss、CELoss
+use_loss: 'AAMLoss'

models/VPR_zhvoice_EcapaTdnn/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c5b0f79add8d1ff11ee06ae58ce423e8fe2e099ebbf2e134713329040001e0
+size 27193761

models/VPR_zhvoice_EcapaTdnn/model.state

@@ -0,0 +1 @@
+{"last_epoch": 28, "eer": 0.019150287201911552, "version": "0.3.9"}

models/VPR_zhvoice_EcapaTdnn/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa197567fdddb8d1fcfc33cb8ccc27a698aab15bc873855050999badf402394
+size 54235141

models/VPR_zhvoice_EcapaTdnn/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/2DIPW/VPR_zhvoice_EcapaTdnn

models/nemo-ecapa-tdnn/.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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/nemo-ecapa-tdnn/model_config.yaml

@@ -0,0 +1,91 @@
+sample_rate: 16000
+train_ds:
+  manifest_filepath: /manifests/combined_fisher_swbd_voxceleb12_librispeech/train.json
+  sample_rate: 16000
+  labels: null
+  batch_size: 64
+  shuffle: true
+  time_length: 3
+  augmentor:
+    noise:
+      manifest_path: /manifests/noise/rir_noise_manifest.json
+      prob: 0.5
+      min_snr_db: 0
+      max_snr_db: 15
+    speed:
+      prob: 0.5
+      sr: 16000
+      resample_type: kaiser_fast
+      min_speed_rate: 0.95
+      max_speed_rate: 1.05
+  num_workers: 15
+  pin_memory: true
+validation_ds:
+  manifest_filepath: /manifests/combined_fisher_swbd_voxceleb12_librispeech/dev.json
+  sample_rate: 16000
+  labels: null
+  batch_size: 64
+  shuffle: false
+  time_length: 3
+  num_workers: 15
+  pin_memory: true
+preprocessor:
+  _target_: nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor
+  normalize: per_feature
+  window_size: 0.025
+  sample_rate: 16000
+  window_stride: 0.01
+  window: hann
+  features: 80
+  n_fft: 512
+  frame_splicing: 1
+  dither: 1.0e-05
+  stft_conv: false
+spec_augment:
+  _target_: nemo.collections.asr.modules.SpectrogramAugmentation
+  freq_masks: 3
+  freq_width: 4
+  time_masks: 5
+  time_width: 0.03
+encoder:
+  _target_: nemo.collections.asr.modules.ECAPAEncoder
+  feat_in: 80
+  filters:
+  - 1024
+  - 1024
+  - 1024
+  - 1024
+  - 3072
+  kernel_sizes:
+  - 5
+  - 3
+  - 3
+  - 3
+  - 1
+  dilations:
+  - 1
+  - 1
+  - 1
+  - 1
+  - 1
+  scale: 8
+decoder:
+  _target_: nemo.collections.asr.modules.SpeakerDecoder
+  feat_in: 3072
+  num_classes: 16681
+  pool_mode: attention
+  emb_sizes: 192
+  angular: true
+loss:
+  scale: 30
+  margin: 0.2
+optim:
+  name: sgd
+  lr: 0.08
+  weight_decay: 0.0002
+  sched:
+    name: CosineAnnealing
+    warmup_ratio: 0.1
+    min_lr: 0.0001
+  momentum: 0.9
+target: nemo.collections.asr.models.label_models.EncDecSpeakerLabelModel

models/nemo-ecapa-tdnn/model_weights.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2146bb8a8aa2b92855e82aeb3ae4a07d4ba7d470647c9650c9fc1b465f6d1e
+size 96765579

models/nemo-ecapa-tdnn/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/huseinzol05/nemo-ecapa-tdnn

models/spkrec-ecapa-voxceleb/.gitattributes

@@ -0,0 +1,19 @@
+*.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
+classifier.ckpt filter=lfs diff=lfs merge=lfs -text
+embedding_model.ckpt filter=lfs diff=lfs merge=lfs -text
+mean_var_norm_emb.ckpt filter=lfs diff=lfs merge=lfs -text

models/spkrec-ecapa-voxceleb/README.md

@@ -0,0 +1,143 @@
+---
+language: "en"
+thumbnail:
+tags:
+- speechbrain
+- embeddings
+- Speaker
+- Verification
+- Identification
+- pytorch
+- ECAPA
+- TDNN
+license: "apache-2.0"
+datasets:
+- voxceleb
+metrics:
+- EER
+widget:
+- example_title: VoxCeleb Speaker id10003
+  src: https://cdn-media.huggingface.co/speech_samples/VoxCeleb1_00003.wav
+- example_title: VoxCeleb Speaker id10004
+  src: https://cdn-media.huggingface.co/speech_samples/VoxCeleb_00004.wav
+---
+
+<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/>
+
+# Speaker Verification with ECAPA-TDNN embeddings on Voxceleb
+
+This repository provides all the necessary tools to perform speaker verification with a pretrained ECAPA-TDNN model using SpeechBrain. 
+The system can be used to extract speaker embeddings as well. 
+It is trained on Voxceleb 1+ Voxceleb2 training data. 
+
+For a better experience, we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io). The model performance on Voxceleb1-test set(Cleaned) is:
+
+| Release | EER(%) 
+|:-------------:|:--------------:|
+| 05-03-21 | 0.80 | 
+
+
+## Pipeline description
+
+This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss.  Speaker Verification is performed using cosine distance between speaker embeddings.
+
+## Install SpeechBrain
+
+First of all, please install SpeechBrain with the following command:
+
+```
+pip install git+https://github.com/speechbrain/speechbrain.git@develop
+```
+
+Please notice that we encourage you to read our tutorials and learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+### Compute your speaker embeddings
+
+```python
+import torchaudio
+from speechbrain.inference.speaker import EncoderClassifier
+classifier = EncoderClassifier.from_hparams(source="speechbrain/spkrec-ecapa-voxceleb")
+signal, fs =torchaudio.load('tests/samples/ASR/spk1_snt1.wav')
+embeddings = classifier.encode_batch(signal)
+```
+The system is trained with recordings sampled at 16kHz (single channel).
+The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *classify_file* if needed. Make sure your input tensor is compliant with the expected sampling rate if you use *encode_batch* and *classify_batch*.
+
+### Perform Speaker Verification
+
+```python
+from speechbrain.inference.speaker import SpeakerRecognition
+verification = SpeakerRecognition.from_hparams(source="speechbrain/spkrec-ecapa-voxceleb", savedir="pretrained_models/spkrec-ecapa-voxceleb")
+score, prediction = verification.verify_files("tests/samples/ASR/spk1_snt1.wav", "tests/samples/ASR/spk2_snt1.wav") # Different Speakers
+score, prediction = verification.verify_files("tests/samples/ASR/spk1_snt1.wav", "tests/samples/ASR/spk1_snt2.wav") # Same Speaker
+```
+ The prediction is 1 if the two signals in input are from the same speaker and 0 otherwise.
+
+### 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 (aa018540).
+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/VoxCeleb/SpeakerRec
+python train_speaker_embeddings.py hparams/train_ecapa_tdnn.yaml --data_folder=your_data_folder
+```
+
+You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1-ahC1xeyPinAHp2oAohL-02smNWO41Cc?usp=sharing).
+
+### Limitations
+The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
+
+#### Referencing ECAPA-TDNN
+```
+@inproceedings{DBLP:conf/interspeech/DesplanquesTD20,
+  author    = {Brecht Desplanques and
+               Jenthe Thienpondt and
+               Kris Demuynck},
+  editor    = {Helen Meng and
+               Bo Xu and
+               Thomas Fang Zheng},
+  title     = {{ECAPA-TDNN:} Emphasized Channel Attention, Propagation and Aggregation
+               in {TDNN} Based Speaker Verification},
+  booktitle = {Interspeech 2020},
+  pages     = {3830--3834},
+  publisher = {{ISCA}},
+  year      = {2020},
+}
+```
+
+# **Citing SpeechBrain**
+Please, cite SpeechBrain if you use it for your research or business.
+
+```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}
+}
+```
+
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/

models/spkrec-ecapa-voxceleb/classifier.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9e3634fe68bd0a427c95e354c0c677374f62b3f434e45b78599950d860d535
+size 5534328

models/spkrec-ecapa-voxceleb/config.json

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

models/spkrec-ecapa-voxceleb/embedding_model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0575cb64845e6b9a10db9bcb74d5ac32b326b8dc90352671d345e2ee3d0126a2
+size 83316686

models/spkrec-ecapa-voxceleb/example1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2dde5cb516939ff619d62fc07d4f4bec5b5d521aee3d07ae51828c9d93be0b
+size 104390

models/spkrec-ecapa-voxceleb/hyperparams.yaml

@@ -0,0 +1,58 @@
+# ############################################################################
+# Model: ECAPA big for Speaker verification
+# ############################################################################
+
+# Feature parameters
+n_mels: 80
+
+# Pretrain folder (HuggingFace)
+pretrained_path: speechbrain/spkrec-ecapa-voxceleb
+
+# Output parameters
+out_n_neurons: 7205
+
+# Model params
+compute_features: !new:speechbrain.lobes.features.Fbank
+    n_mels: !ref <n_mels>
+
+mean_var_norm: !new:speechbrain.processing.features.InputNormalization
+    norm_type: sentence
+    std_norm: False
+
+embedding_model: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
+    input_size: !ref <n_mels>
+    channels: [1024, 1024, 1024, 1024, 3072]
+    kernel_sizes: [5, 3, 3, 3, 1]
+    dilations: [1, 2, 3, 4, 1]
+    attention_channels: 128
+    lin_neurons: 192
+
+classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
+    input_size: 192
+    out_neurons: !ref <out_n_neurons>
+
+mean_var_norm_emb: !new:speechbrain.processing.features.InputNormalization
+    norm_type: global
+    std_norm: False
+
+modules:
+    compute_features: !ref <compute_features>
+    mean_var_norm: !ref <mean_var_norm>
+    embedding_model: !ref <embedding_model>
+    mean_var_norm_emb: !ref <mean_var_norm_emb>
+    classifier: !ref <classifier>
+        
+label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
+
+        
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        embedding_model: !ref <embedding_model>
+        mean_var_norm_emb: !ref <mean_var_norm_emb>
+        classifier: !ref <classifier>
+        label_encoder: !ref <label_encoder>
+    paths:
+        embedding_model: !ref <pretrained_path>/embedding_model.ckpt
+        mean_var_norm_emb: !ref <pretrained_path>/mean_var_norm_emb.ckpt
+        classifier: !ref <pretrained_path>/classifier.ckpt
+        label_encoder: !ref <pretrained_path>/label_encoder.txt

models/spkrec-ecapa-voxceleb/mean_var_norm_emb.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd70225b05b37be64fc5a95e24395d804231d43f74b2e1e5a513db7b69b34c33
+size 1921

models/spkrec-ecapa-voxceleb/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb