ECAPA-TDNN (wespeaker ONNX models)

models/wespeaker-ecapa-tdnn512-LM/.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/wespeaker-ecapa-tdnn512-LM/README.md

@@ -0,0 +1,100 @@
+---
+license: cc-by-4.0
+language:
+- en
+pipeline_tag: summarization
+tags:
+- speaker embedding
+- wespeaker
+- speaker modelling
+---
+
+
+Official model provided by [Wespeaker](https://github.com/wenet-e2e/wespeaker) project, ECAPA-TDNN based x-vector (After large margin finetune)
+
+The model is trained on VoxCeleb2 Dev dataset, containing 5994 speakers.
+
+
+## Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/wenet-e2e/wespeaker
+- **Paper:** https://arxiv.org/pdf/2210.17016.pdf
+- **Demo:** https://huggingface.co/spaces/wenet/wespeaker_demo
+
+
+## Results on VoxCeleb
+| Model | Params | Flops | LM | AS-Norm | vox1-O-clean | vox1-E-clean | vox1-H-clean |
+|:------|:------:|:------|:--:|:-------:|:------------:|:------------:|:------------:|
+| ECAPA_TDNN_GLOB_c512-ASTP-emb192  | 6.19M | 1.04G | × | × | 1.069 | 1.209 | 2.310 |
+|                                   |       |       | × | √ | 0.957 | 1.128 | 2.105 |
+|                                   |       |       | √ | × | 0.878 | 1.072 | 2.007 |
+|                                   |       |       | √ | √ | 0.782 | 1.005 | 1.824 |
+
+## Install Wespeaker
+
+``` sh
+pip install git+https://github.com/wenet-e2e/wespeaker.git
+```
+
+for development install:
+
+``` sh
+git clone https://github.com/wenet-e2e/wespeaker.git
+cd wespeaker
+pip install -e .
+```
+
+
+### Command line Usage
+
+``` sh
+$ wespeaker -p ecapa_tdnn512_download_dir --task embedding --audio_file audio.wav --output_file embedding.txt
+$ wespeaker -p ecapa_tdnn512_download_dir --task embedding_kaldi --wav_scp wav.scp --output_file /path/to/embedding
+$ wespeaker -p ecapa_tdnn512_download_dir --task similarity --audio_file audio.wav --audio_file2 audio2.wav
+$ wespeaker -p ecapa_tdnn512_download_dir --task diarization --audio_file audio.wav
+```
+
+### Python Programming Usage
+
+``` python
+import wespeaker
+
+model = wespeaker.load_model_local(ecapa_tdnn512_download_dir)
+# set_gpu to enable the cuda inference, number < 0 means using CPU
+model.set_gpu(0)
+
+# embedding/embedding_kaldi/similarity/diarization
+embedding = model.extract_embedding('audio.wav')
+utt_names, embeddings = model.extract_embedding_list('wav.scp')
+similarity = model.compute_similarity('audio1.wav', 'audio2.wav')
+diar_result = model.diarize('audio.wav')
+
+# register and recognize
+model.register('spk1', 'spk1_audio1.wav')
+model.register('spk2', 'spk2_audio1.wav')
+model.register('spk3', 'spk3_audio1.wav')
+result = model.recognize('spk1_audio2.wav')
+```
+
+## Citation
+
+
+```bibtex
+@article{desplanques2020ecapa,
+  title={Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification},
+  author={Desplanques, Brecht and Thienpondt, Jenthe and Demuynck, Kris},
+  journal={arXiv preprint arXiv:2005.07143},
+  year={2020}
+}
+
+@inproceedings{wang2023wespeaker,
+  title={Wespeaker: A research and production oriented speaker embedding learning toolkit},
+  author={Wang, Hongji and Liang, Chengdong and Wang, Shuai and Chen, Zhengyang and Zhang, Binbin and Xiang, Xu and Deng, Yanlei and Qian, Yanmin},
+  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={1--5},
+  year={2023},
+  organization={IEEE}
+}
+```

models/wespeaker-ecapa-tdnn512-LM/avg_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c3cdaae5aba872ea888c904f5f4fd9fa41651ec072b1ebf40d611eb93e8d3e
+size 38708805

models/wespeaker-ecapa-tdnn512-LM/config.yaml

@@ -0,0 +1,77 @@
+data_type: shard
+dataloader_args:
+  batch_size: 128
+  drop_last: true
+  num_workers: 16
+  pin_memory: false
+  prefetch_factor: 8
+dataset_args:
+  aug_prob: 0.6
+  fbank_args:
+    dither: 1.0
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  num_frms: 200
+  shuffle: true
+  shuffle_args:
+    shuffle_size: 2500
+  spec_aug: false
+  spec_aug_args:
+    max_f: 8
+    max_t: 10
+    num_f_mask: 1
+    num_t_mask: 1
+    prob: 0.6
+  speed_perturb: true
+exp_dir: exp/ECAPA_TDNN_GLOB_c512-ASTP-emb192-fbank80-num_frms200-aug0.6-spTrue-saFalse-ArcMargin-SGD-epoch150
+gpus:
+- 0
+- 1
+log_batch_interval: 100
+loss: CrossEntropyLoss
+loss_args: {}
+margin_scheduler: MarginScheduler
+margin_update:
+  epoch_iter: 4265
+  final_margin: 0.2
+  fix_start_epoch: 40
+  increase_start_epoch: 20
+  increase_type: exp
+  initial_margin: 0.0
+  update_margin: true
+model: ECAPA_TDNN_GLOB_c512
+model_args:
+  embed_dim: 192
+  feat_dim: 80
+  pooling_func: ASTP
+model_init: null
+noise_data: data/musan/lmdb
+num_avg: 10
+num_epochs: 150
+optimizer: SGD
+optimizer_args:
+  lr: 0.1
+  momentum: 0.9
+  nesterov: true
+  weight_decay: 0.0001
+projection_args:
+  easy_margin: false
+  embed_dim: 192
+  num_class: 17982
+  project_type: arc_margin
+  scale: 32.0
+reverb_data: data/rirs/lmdb
+save_epoch_interval: 5
+scheduler: ExponentialDecrease
+scheduler_args:
+  epoch_iter: 4265
+  final_lr: 5.0e-05
+  initial_lr: 0.1
+  num_epochs: 150
+  scale_ratio: 4.0
+  warm_from_zero: true
+  warm_up_epoch: 6
+seed: 42
+train_data: data/vox2_dev/shard.list
+train_label: data/vox2_dev/utt2spk

models/wespeaker-ecapa-tdnn512-LM/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Wespeaker/wespeaker-ecapa-tdnn512-LM

models/wespeaker-ecapa-tdnn512-LM/voxceleb_ECAPA512_LM.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71b85d9b48058ef68004f04f1b78acebefb9dfcf542e19b976a12a5ad1f10b0
+size 24861931

models/wespeaker-voxceleb-ecapa-tdnn1024-LM/.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/wespeaker-voxceleb-ecapa-tdnn1024-LM/README.md

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

models/wespeaker-voxceleb-ecapa-tdnn1024-LM/avg_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf97861486c3900862948f555582b151dcd8fc05616c719f66233016493b22c
+size 72613701

models/wespeaker-voxceleb-ecapa-tdnn1024-LM/config.yaml

@@ -0,0 +1,77 @@
+data_type: shard
+dataloader_args:
+  batch_size: 128
+  drop_last: true
+  num_workers: 16
+  pin_memory: false
+  prefetch_factor: 8
+dataset_args:
+  aug_prob: 0.6
+  fbank_args:
+    dither: 1.0
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  num_frms: 200
+  shuffle: true
+  shuffle_args:
+    shuffle_size: 2500
+  spec_aug: false
+  spec_aug_args:
+    max_f: 8
+    max_t: 10
+    num_f_mask: 1
+    num_t_mask: 1
+    prob: 0.6
+  speed_perturb: true
+exp_dir: exp/ECAPA_TDNN_GLOB_c1024-ASTP-emb192-fbank80-num_frms200-aug0.6-spTrue-saFalse-ArcMargin-SGD-epoch150
+gpus:
+- 0
+- 1
+log_batch_interval: 100
+loss: CrossEntropyLoss
+loss_args: {}
+margin_scheduler: MarginScheduler
+margin_update:
+  epoch_iter: 4265
+  final_margin: 0.2
+  fix_start_epoch: 40
+  increase_start_epoch: 20
+  increase_type: exp
+  initial_margin: 0.0
+  update_margin: true
+model: ECAPA_TDNN_GLOB_c1024
+model_args:
+  embed_dim: 192
+  feat_dim: 80
+  pooling_func: ASTP
+model_init: null
+noise_data: data/musan/lmdb
+num_avg: 10
+num_epochs: 150
+optimizer: SGD
+optimizer_args:
+  lr: 0.1
+  momentum: 0.9
+  nesterov: true
+  weight_decay: 0.0001
+projection_args:
+  easy_margin: false
+  embed_dim: 192
+  num_class: 17982
+  project_type: arc_margin
+  scale: 32.0
+reverb_data: data/rirs/lmdb
+save_epoch_interval: 5
+scheduler: ExponentialDecrease
+scheduler_args:
+  epoch_iter: 4265
+  final_lr: 5.0e-05
+  initial_lr: 0.1
+  num_epochs: 150
+  scale_ratio: 4.0
+  warm_from_zero: true
+  warm_up_epoch: 6
+seed: 42
+train_data: data/vox2_dev/shard.list
+train_label: data/vox2_dev/utt2spk

models/wespeaker-voxceleb-ecapa-tdnn1024-LM/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Wespeaker/wespeaker-voxceleb-ecapa-tdnn1024-LM

models/wespeaker-voxceleb-ecapa-tdnn1024-LM/voxceleb_ECAPA1024_LM.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d2dbefe9a66d161b6dfd819e425270939a17a932bd9cbfeea85e2061c0929b
+size 58766986

models/wespeaker-voxceleb-ecapa-tdnn1024/.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/wespeaker-voxceleb-ecapa-tdnn1024/README.md

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

models/wespeaker-voxceleb-ecapa-tdnn1024/avg_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b643b3dd1201c3c42a6120c1aed4bfd5b2e01dd072c2dc9600c6d180fa970cb3
+size 72613701

models/wespeaker-voxceleb-ecapa-tdnn1024/config.yaml

@@ -0,0 +1,77 @@
+data_type: shard
+dataloader_args:
+  batch_size: 128
+  drop_last: true
+  num_workers: 16
+  pin_memory: false
+  prefetch_factor: 8
+dataset_args:
+  aug_prob: 0.6
+  fbank_args:
+    dither: 1.0
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  num_frms: 200
+  shuffle: true
+  shuffle_args:
+    shuffle_size: 2500
+  spec_aug: false
+  spec_aug_args:
+    max_f: 8
+    max_t: 10
+    num_f_mask: 1
+    num_t_mask: 1
+    prob: 0.6
+  speed_perturb: true
+exp_dir: exp/ECAPA_TDNN_GLOB_c1024-ASTP-emb192-fbank80-num_frms200-aug0.6-spTrue-saFalse-ArcMargin-SGD-epoch150
+gpus:
+- 0
+- 1
+log_batch_interval: 100
+loss: CrossEntropyLoss
+loss_args: {}
+margin_scheduler: MarginScheduler
+margin_update:
+  epoch_iter: 4265
+  final_margin: 0.2
+  fix_start_epoch: 40
+  increase_start_epoch: 20
+  increase_type: exp
+  initial_margin: 0.0
+  update_margin: true
+model: ECAPA_TDNN_GLOB_c1024
+model_args:
+  embed_dim: 192
+  feat_dim: 80
+  pooling_func: ASTP
+model_init: null
+noise_data: data/musan/lmdb
+num_avg: 10
+num_epochs: 150
+optimizer: SGD
+optimizer_args:
+  lr: 0.1
+  momentum: 0.9
+  nesterov: true
+  weight_decay: 0.0001
+projection_args:
+  easy_margin: false
+  embed_dim: 192
+  num_class: 17982
+  project_type: arc_margin
+  scale: 32.0
+reverb_data: data/rirs/lmdb
+save_epoch_interval: 5
+scheduler: ExponentialDecrease
+scheduler_args:
+  epoch_iter: 4265
+  final_lr: 5.0e-05
+  initial_lr: 0.1
+  num_epochs: 150
+  scale_ratio: 4.0
+  warm_from_zero: true
+  warm_up_epoch: 6
+seed: 42
+train_data: data/vox2_dev/shard.list
+train_label: data/vox2_dev/utt2spk

models/wespeaker-voxceleb-ecapa-tdnn1024/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Wespeaker/wespeaker-voxceleb-ecapa-tdnn1024

models/wespeaker-voxceleb-ecapa-tdnn1024/voxceleb_ECAPA1024.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1eab5f9b8b91aa1686881cbbca3997046e000b9e42e19f25212cb624d5d6d09
+size 58766986

models/wespeaker-voxceleb-ecapa-tdnn512/.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/wespeaker-voxceleb-ecapa-tdnn512/README.md

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

models/wespeaker-voxceleb-ecapa-tdnn512/avg_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5659521b311ce284751b7a7e8897e9287b7b9131db00ad58f35807b49515f6a
+size 38708805

models/wespeaker-voxceleb-ecapa-tdnn512/config.yaml

@@ -0,0 +1,77 @@
+data_type: shard
+dataloader_args:
+  batch_size: 128
+  drop_last: true
+  num_workers: 16
+  pin_memory: false
+  prefetch_factor: 8
+dataset_args:
+  aug_prob: 0.6
+  fbank_args:
+    dither: 1.0
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  num_frms: 200
+  shuffle: true
+  shuffle_args:
+    shuffle_size: 2500
+  spec_aug: false
+  spec_aug_args:
+    max_f: 8
+    max_t: 10
+    num_f_mask: 1
+    num_t_mask: 1
+    prob: 0.6
+  speed_perturb: true
+exp_dir: exp/ECAPA_TDNN_GLOB_c512-ASTP-emb192-fbank80-num_frms200-aug0.6-spTrue-saFalse-ArcMargin-SGD-epoch150
+gpus:
+- 0
+- 1
+log_batch_interval: 100
+loss: CrossEntropyLoss
+loss_args: {}
+margin_scheduler: MarginScheduler
+margin_update:
+  epoch_iter: 4265
+  final_margin: 0.2
+  fix_start_epoch: 40
+  increase_start_epoch: 20
+  increase_type: exp
+  initial_margin: 0.0
+  update_margin: true
+model: ECAPA_TDNN_GLOB_c512
+model_args:
+  embed_dim: 192
+  feat_dim: 80
+  pooling_func: ASTP
+model_init: null
+noise_data: data/musan/lmdb
+num_avg: 10
+num_epochs: 150
+optimizer: SGD
+optimizer_args:
+  lr: 0.1
+  momentum: 0.9
+  nesterov: true
+  weight_decay: 0.0001
+projection_args:
+  easy_margin: false
+  embed_dim: 192
+  num_class: 17982
+  project_type: arc_margin
+  scale: 32.0
+reverb_data: data/rirs/lmdb
+save_epoch_interval: 5
+scheduler: ExponentialDecrease
+scheduler_args:
+  epoch_iter: 4265
+  final_lr: 5.0e-05
+  initial_lr: 0.1
+  num_epochs: 150
+  scale_ratio: 4.0
+  warm_from_zero: true
+  warm_up_epoch: 6
+seed: 42
+train_data: data/vox2_dev/shard.list
+train_label: data/vox2_dev/utt2spk

models/wespeaker-voxceleb-ecapa-tdnn512/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Wespeaker/wespeaker-voxceleb-ecapa-tdnn512

models/wespeaker-voxceleb-ecapa-tdnn512/voxceleb_ECAPA512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f901ae3571912bad4e11e157744cb8b7d77a0b46923b83c410bdbb6c77d69736
+size 24861931