espnet / cnceleb_ecapa_tdnn

huggingface.co
Total runs: 13
24-hour runs: -1
7-day runs: -7
30-day runs: -1
Model's Last Updated: September 20 2026
audio-classification

Introduction of cnceleb_ecapa_tdnn

Model Details of cnceleb_ecapa_tdnn

ESPnet2 SPK model
espnet/cnceleb_ecapa_tdnn

This model was trained by holvan using cnceleb recipe in espnet .

Demo: How to use in ESPnet2

Follow the ESPnet installation instructions if you haven't done that already.

cd espnet
git checkout d3db63621b5ea1d7b450d768f97c1a6bdf3cf8be
pip install -e .
cd egs2/cnceleb/spk1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/cnceleb_ecapa_tdnn

RESULTS

Environments

date: 2025-06-17 13:12:33.497674

  • python version: 3.10.14 (main, May 6 2024, 19:42:50) [GCC 11.2.0]
  • espnet version: 202402
  • pytorch version: 2.3.1
Mean Std
Target -1.0389 0.1553
Non-target -1.3574 0.0679
Model name EER(%) minDCF
conf/train_ecapa_tdnn 7.762 0.35304
SPK config
expand
config: conf/train_ecapa_tdnn.yaml
print_config: false
log_level: INFO
drop_last_iter: true
dry_run: false
iterator_type: category
valid_iterator_type: sequence
output_dir: exp/spk_train_ecapa_tdnn_raw_sp
ngpu: 1
seed: 0
num_workers: 8
num_att_plot: 0
dist_backend: nccl
dist_init_method: env://
dist_world_size: 4
dist_rank: 0
local_rank: 0
dist_master_addr: localhost
dist_master_port: 44223
dist_launcher: null
multiprocessing_distributed: true
unused_parameters: false
sharded_ddp: false
use_deepspeed: false
deepspeed_config: null
gradient_as_bucket_view: true
ddp_comm_hook: null
cudnn_enabled: true
cudnn_benchmark: true
cudnn_deterministic: false
use_tf32: false
collect_stats: false
write_collected_feats: false
max_epoch: 40
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - eer
    - min
keep_nbest_models: 3
nbest_averaging_interval: 0
grad_clip: 9999
grad_clip_type: 2.0
grad_noise: false
accum_grad: 1
no_forward_run: false
resume: true
train_dtype: float32
use_amp: true
log_interval: 100
use_matplotlib: true
use_tensorboard: true
create_graph_in_tensorboard: false
use_wandb: false
wandb_project: null
wandb_id: null
wandb_entity: null
wandb_name: null
wandb_model_log_interval: -1
detect_anomaly: false
use_adapter: false
adapter: lora
save_strategy: all
adapter_conf: {}
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 512
valid_batch_size: 40
batch_bins: 1000000
valid_batch_bins: null
category_sample_size: 10
train_shape_file:
- exp/spk_stats_16k_sp/train/speech_shape
valid_shape_file:
- exp/spk_stats_16k_sp/valid/speech_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 120000
sort_in_batch: descending
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
chunk_length: 500
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
chunk_excluded_key_prefixes: []
chunk_default_fs: null
chunk_max_abs_length: null
chunk_discard_short_samples: true
train_data_path_and_name_and_type:
-   - dump/raw/cnceleb_train_sp/wav.scp
    - speech
    - sound
-   - dump/raw/cnceleb_train_sp/utt2spk
    - spk_labels
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/cnceleb1_valid/trial.scp
    - speech
    - sound
-   - dump/raw/cnceleb1_valid/trial2.scp
    - speech2
    - sound
-   - dump/raw/cnceleb1_valid/trial_label
    - spk_labels
    - text
multi_task_dataset: false
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
allow_multi_rates: false
valid_max_cache_size: null
exclude_weight_decay: false
exclude_weight_decay_conf: {}
optim: sgd
optim_conf:
    lr: 0.1
    momentum: 0.9
    weight_decay: 0.0001
scheduler: exponentialdecaywarmup
scheduler_conf:
    max_lr: 0.1
    min_lr: 5.0e-05
    total_steps: 140720
    warmup_steps: 17590
    warm_from_zero: true
init: null
use_preprocessor: true
input_size: null
target_duration: 3.0
spk2utt: dump/raw/cnceleb_train_sp/spk2utt
spk_num: 8379
sample_rate: 16000
num_eval: 10
rir_scp: ''
model_conf:
    extract_feats_in_collect_stats: false
frontend: melspec_torch
frontend_conf:
    preemp: true
    n_fft: 512
    log: true
    win_length: 400
    hop_length: 160
    n_mels: 80
    normalize: mn
specaug: null
specaug_conf: {}
normalize: null
normalize_conf: {}
encoder: ecapa_tdnn
encoder_conf:
    model_scale: 8
    ndim: 1024
    output_size: 1536
pooling: chn_attn_stat
pooling_conf: {}
projector: rawnet3
projector_conf:
    output_size: 192
preprocessor: spk
preprocessor_conf:
    target_duration: 3.0
    sample_rate: 16000
    num_eval: 5
    noise_apply_prob: 0.5
    noise_info:
    -   - 1.0
        - dump/raw/musan_speech.scp
        -   - 4
            - 7
        -   - 13
            - 20
    -   - 1.0
        - dump/raw/musan_noise.scp
        -   - 1
            - 1
        -   - 0
            - 15
    -   - 1.0
        - dump/raw/musan_music.scp
        -   - 1
            - 1
        -   - 5
            - 15
    rir_apply_prob: 0.5
    rir_scp: dump/raw/rirs.scp
loss: aamsoftmax_sc_topk
loss_conf:
    margin: 0.3
    scale: 30
    K: 3
    mp: 0.06
    k_top: 5
required:
- output_dir
version: '202402'
distributed: true
Citing ESPnet
@inproceedings{watanabe2018espnet,
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  title={{ESPnet}: End-to-End Speech Processing Toolkit},
  year={2018},
  booktitle={Proceedings of Interspeech},
  pages={2207--2211},
  doi={10.21437/Interspeech.2018-1456},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}





or arXiv:

@misc{watanabe2018espnet,
  title={ESPnet: End-to-End Speech Processing Toolkit},
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  year={2018},
  eprint={1804.00015},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

Runs of espnet cnceleb_ecapa_tdnn on huggingface.co

13
Total runs
-1
24-hour runs
-9
3-day runs
-7
7-day runs
-1
30-day runs

More Information About cnceleb_ecapa_tdnn huggingface.co Model

More cnceleb_ecapa_tdnn license Visit here:

https://choosealicense.com/licenses/cc-by-4.0

cnceleb_ecapa_tdnn huggingface.co

cnceleb_ecapa_tdnn huggingface.co is an AI model on huggingface.co that provides cnceleb_ecapa_tdnn's model effect (), which can be used instantly with this espnet cnceleb_ecapa_tdnn model. huggingface.co supports a free trial of the cnceleb_ecapa_tdnn model, and also provides paid use of the cnceleb_ecapa_tdnn. Support call cnceleb_ecapa_tdnn model through api, including Node.js, Python, http.

cnceleb_ecapa_tdnn huggingface.co Url

https://huggingface.co/espnet/cnceleb_ecapa_tdnn

espnet cnceleb_ecapa_tdnn online free

cnceleb_ecapa_tdnn huggingface.co is an online trial and call api platform, which integrates cnceleb_ecapa_tdnn's modeling effects, including api services, and provides a free online trial of cnceleb_ecapa_tdnn, you can try cnceleb_ecapa_tdnn online for free by clicking the link below.

espnet cnceleb_ecapa_tdnn online free url in huggingface.co:

https://huggingface.co/espnet/cnceleb_ecapa_tdnn

cnceleb_ecapa_tdnn install

cnceleb_ecapa_tdnn is an open source model from GitHub that offers a free installation service, and any user can find cnceleb_ecapa_tdnn on GitHub to install. At the same time, huggingface.co provides the effect of cnceleb_ecapa_tdnn install, users can directly use cnceleb_ecapa_tdnn installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

cnceleb_ecapa_tdnn install url in huggingface.co:

https://huggingface.co/espnet/cnceleb_ecapa_tdnn

Url of cnceleb_ecapa_tdnn

cnceleb_ecapa_tdnn huggingface.co Url

Provider of cnceleb_ecapa_tdnn huggingface.co

espnet
ORGANIZATIONS

Other API from espnet

huggingface.co

Total runs: 11.1K
Run Growth: -126
Growth Rate: -1.13%
Updated:October 11 2026
huggingface.co

Total runs: 3.5K
Run Growth: -1.2K
Growth Rate: -30.25%
Updated:September 18 2026
huggingface.co

Total runs: 249
Run Growth: 148
Growth Rate: 59.44%
Updated:January 22 2026
huggingface.co

Total runs: 187
Run Growth: 130
Growth Rate: 69.52%
Updated:September 20 2026
huggingface.co

Total runs: 129
Run Growth: 73
Growth Rate: 56.15%
Updated:October 11 2026
huggingface.co

Total runs: 94
Run Growth: 43
Growth Rate: 47.78%
Updated:June 17 2025
huggingface.co

Total runs: 24
Run Growth: 21
Growth Rate: 77.78%
Updated:October 11 2026
huggingface.co

Total runs: 19
Run Growth: 16
Growth Rate: 84.21%
Updated:May 03 2025
huggingface.co

Total runs: 14
Run Growth: 5
Growth Rate: 33.33%
Updated:August 26 2024