espnet / opencpop_xiaoice

huggingface.co
Total runs: 20
24-hour runs: 0
7-day runs: 0
30-day runs: 9
Model's Last Updated: September 18 2026
text-to-speech

Introduction of opencpop_xiaoice

Model Details of opencpop_xiaoice

ESPnet2 SVS model
espnet/opencpop_xiaoice

This model was trained by ftshijt using opencpop 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 5c4d7cf7feba8461de2e1080bf82182f0efaef38
pip install -e .
cd egs2/opencpop/svs1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/opencpop_xiaoice
SVS config
expand
config: conf/tuning/train_xiaoice.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: exp/svs_train_xiaoice_raw_phn_None_zh
ngpu: 1
seed: 0
num_workers: 10
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: null
dist_rank: null
local_rank: 0
dist_master_addr: null
dist_master_port: null
dist_launcher: null
multiprocessing_distributed: false
unused_parameters: false
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 500
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - loss
    - min
-   - train
    - loss
    - min
keep_nbest_models: 5
nbest_averaging_interval: 0
grad_clip: 1.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 1
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
log_interval: null
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_lora: false
save_lora_only: true
lora_conf: {}
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 16
valid_batch_size: null
batch_bins: 1000000
valid_batch_bins: null
train_shape_file:
- exp/svs_stats_raw_phn_None_zh/train/text_shape.phn
- exp/svs_stats_raw_phn_None_zh/train/singing_shape
valid_shape_file:
- exp/svs_stats_raw_phn_None_zh/valid/text_shape.phn
- exp/svs_stats_raw_phn_None_zh/valid/singing_shape
batch_type: sorted
valid_batch_type: null
fold_length:
- 150
- 240000
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
train_data_path_and_name_and_type:
-   - dump24k/raw/tr_no_dev/text
    - text
    - text
-   - dump24k/raw/tr_no_dev/wav.scp
    - singing
    - sound
-   - dump24k/raw/tr_no_dev/label
    - label
    - duration
-   - dump24k/raw/tr_no_dev/score.scp
    - score
    - score
-   - exp/svs_stats_raw_phn_None_zh/train/collect_feats/pitch.scp
    - pitch
    - npy
-   - exp/svs_stats_raw_phn_None_zh/train/collect_feats/feats.scp
    - feats
    - npy
valid_data_path_and_name_and_type:
-   - dump24k/raw/dev/text
    - text
    - text
-   - dump24k/raw/dev/wav.scp
    - singing
    - sound
-   - dump24k/raw/dev/label
    - label
    - duration
-   - dump24k/raw/dev/score.scp
    - score
    - score
-   - exp/svs_stats_raw_phn_None_zh/valid/collect_feats/pitch.scp
    - pitch
    - npy
-   - exp/svs_stats_raw_phn_None_zh/valid/collect_feats/feats.scp
    - feats
    - npy
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: adam
optim_conf:
    lr: 0.001
    eps: 1.0e-06
    weight_decay: 0.0
scheduler: null
scheduler_conf: {}
token_list:
- <blank>
- <unk>
- SP
- i
- AP
- e
- y
- d
- w
- sh
- ai
- n
- x
- j
- ian
- u
- l
- h
- b
- o
- zh
- an
- ou
- m
- q
- z
- en
- g
- ing
- ei
- ao
- ang
- uo
- eng
- t
- a
- ong
- ui
- k
- f
- r
- iang
- ch
- v
- in
- iao
- ie
- iu
- c
- s
- van
- p
- ve
- uan
- uang
- ia
- ua
- uai
- un
- er
- vn
- iong
- <sos/eos>
odim: null
model_conf: {}
use_preprocessor: true
token_type: phn
bpemodel: null
non_linguistic_symbols: null
cleaner: null
g2p: null
fs: 24000
score_feats_extract: syllable_score_feats
score_feats_extract_conf:
    fs: 24000
    n_fft: 2048
    win_length: 1200
    hop_length: 300
feats_extract: fbank
feats_extract_conf:
    n_fft: 2048
    hop_length: 300
    win_length: 1200
    fs: 24000
    fmin: 80
    fmax: 7600
    n_mels: 80
normalize: global_mvn
normalize_conf:
    stats_file: exp/svs_stats_raw_phn_None_zh/train/feats_stats.npz
svs: xiaoice
svs_conf:
    midi_dim: 129
    duration_dim: 512
    adim: 384
    aheads: 4
    elayers: 6
    eunits: 1536
    dlayers: 6
    dunits: 1536
    postnet_layers: 5
    postnet_chans: 512
    postnet_filts: 5
    postnet_dropout_rate: 0.5
    use_batch_norm: true
    reduction_factor: 1
    init_type: pytorch
    use_masking: true
    loss_function: XiaoiceSing2
    loss_type: L1
    lambda_mel: 1
    lambda_dur: 0.1
    lambda_pitch: 0.01
    lambda_vuv: 0.01
pitch_extract: dio
pitch_extract_conf:
    use_token_averaged_f0: false
    fs: 24000
    n_fft: 2048
    hop_length: 300
    f0max: 800
    f0min: 80
    reduction_factor: 1
pitch_normalize: global_mvn
pitch_normalize_conf:
    stats_file: exp/svs_stats_raw_phn_None_zh/train/pitch_stats.npz
ying_extract: null
ying_extract_conf: {}
energy_extract: null
energy_extract_conf: {}
energy_normalize: null
energy_normalize_conf: {}
required:
- output_dir
- token_list
version: '202310'
distributed: false
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}
}






@inproceedings{shi22d_interspeech,
  author={Jiatong Shi and Shuai Guo and Tao Qian and Tomoki Hayashi and Yuning Wu and Fangzheng Xu and Xuankai Chang and Huazhe Li and Peter Wu and Shinji Watanabe and Qin Jin},
  title={{Muskits: an End-to-end Music Processing Toolkit for Singing Voice Synthesis}},
  year=2022,
  booktitle={Proc. Interspeech 2022},
  pages={4277--4281},
  doi={10.21437/Interspeech.2022-10039}
}

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 opencpop_xiaoice on huggingface.co

20
Total runs
0
24-hour runs
1
3-day runs
0
7-day runs
9
30-day runs

More Information About opencpop_xiaoice huggingface.co Model

More opencpop_xiaoice license Visit here:

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

opencpop_xiaoice huggingface.co

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

opencpop_xiaoice huggingface.co Url

https://huggingface.co/espnet/opencpop_xiaoice

espnet opencpop_xiaoice online free

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

espnet opencpop_xiaoice online free url in huggingface.co:

https://huggingface.co/espnet/opencpop_xiaoice

opencpop_xiaoice install

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

opencpop_xiaoice install url in huggingface.co:

https://huggingface.co/espnet/opencpop_xiaoice

Url of opencpop_xiaoice

opencpop_xiaoice huggingface.co Url

Provider of opencpop_xiaoice huggingface.co

espnet
ORGANIZATIONS

Other API from espnet

huggingface.co

Total runs: 13.1K
Run Growth: 1.4K
Growth Rate: 10.88%
Updated:October 11 2026
huggingface.co

Total runs: 2.7K
Run Growth: -2.2K
Growth Rate: -80.90%
Updated:September 18 2026
huggingface.co

Total runs: 577
Run Growth: 455
Growth Rate: 78.86%
Updated:September 20 2026
huggingface.co

Total runs: 509
Run Growth: 307
Growth Rate: 60.31%
Updated:January 22 2026
huggingface.co

Total runs: 190
Run Growth: 122
Growth Rate: 64.55%
Updated:October 11 2026
huggingface.co

Total runs: 77
Run Growth: 1
Growth Rate: 1.30%
Updated:June 17 2025
huggingface.co

Total runs: 26
Run Growth: 1
Growth Rate: 4.17%
Updated:October 11 2026
huggingface.co

Total runs: 25
Run Growth: 12
Growth Rate: 50.00%
Updated:August 26 2024
huggingface.co

Total runs: 22
Run Growth: 4
Growth Rate: 18.18%
Updated:September 20 2026
huggingface.co

Total runs: 22
Run Growth: 13
Growth Rate: 61.90%
Updated:May 03 2025
huggingface.co

Total runs: 21
Run Growth: 8
Growth Rate: 38.10%
Updated:September 20 2026
huggingface.co

Total runs: 20
Run Growth: 6
Growth Rate: 31.58%
Updated:September 20 2026
huggingface.co

Total runs: 17
Run Growth: 6
Growth Rate: 33.33%
Updated:May 03 2025
huggingface.co

Total runs: 17
Run Growth: 7
Growth Rate: 36.84%
Updated:May 03 2025