You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/docs/source/released_model.md

7.9 KiB

Released Models

Speech-To-Text Models

Acoustic Model Released in paddle 2.X

Acoustic Model Training Data Token-based Size Descriptions CER WER Hours of speech
Ds2 Online Aishell Model Aishell Dataset Char-based 345 MB 2 Conv + 5 LSTM layers with only forward direction 0.080218 - 151 h
Ds2 Offline Aishell Model Aishell Dataset Char-based 306 MB 2 Conv + 3 bidirectional GRU layers 0.065 - 151 h
Conformer Online Aishell Model Aishell Dataset Char-based 283 MB Encoder:Conformer, Decoder:Transformer, Decoding method: Attention + CTC 0.0594 - 151 h
Conformer Offline Aishell Model Aishell Dataset Char-based 284 MB Encoder:Conformer, Decoder:Transformer, Decoding method: Attention 0.0547 - 151 h
Conformer Librispeech Model Librispeech Dataset Word-based 287 MB Encoder:Conformer, Decoder:Transformer, Decoding method: Attention - 0.0325 960 h
Transformer Librispeech Model Librispeech Dataset Word-based 195 MB Encoder:Transformer, Decoder:Transformer, Decoding method: Attention - 0.0544 960 h

Acoustic Model Transformed from paddle 1.8

Acoustic Model Training Data Token-based Size Descriptions CER WER Hours of speech
Ds2 Offline Aishell model Aishell Dataset Char-based 234 MB 2 Conv + 3 bidirectional GRU layers 0.0804 - 151 h
Ds2 Offline Librispeech model Librispeech Dataset Word-based 307 MB 2 Conv + 3 bidirectional sharing weight RNN layers - 0.0685 960 h
Ds2 Offline Baidu en8k model Baidu Internal English Dataset Word-based 273 MB 2 Conv + 3 bidirectional GRU layers - 0.0541 8628 h

Language Model Released

Language Model Training Data Token-based Size Descriptions
English LM CommonCrawl(en.00) Word-based 8.3 GB Pruned with 0 1 1 1 1;
About 1.85 billion n-grams;
'trie' binary with '-a 22 -q 8 -b 8'
Mandarin LM Small Baidu Internal Corpus Char-based 2.8 GB Pruned with 0 1 2 4 4;
About 0.13 billion n-grams;
'probing' binary with default settings
Mandarin LM Large Baidu Internal Corpus Char-based 70.4 GB No Pruning;
About 3.7 billion n-grams;
'probing' binary with default settings

Text-To-Speech Models

Acoustic Models

Model Type Dataset Example Link Pretrained Models Static Models Siize(static)
Tacotron2 LJSpeech tacotron2-vctk tacotron2_ljspeech_ckpt_0.3.zip
TransformerTTS LJSpeech transformer-ljspeech transformer_tts_ljspeech_ckpt_0.4.zip
SpeedySpeech CSMSC speedyspeech-csmsc speedyspeech_nosil_baker_ckpt_0.5.zip speedyspeech_nosil_baker_static_0.5.zip 12MB
FastSpeech2 CSMSC fastspeech2-csmsc fastspeech2_nosil_baker_ckpt_0.4.zip fastspeech2_nosil_baker_static_0.4.zip 157MB
FastSpeech2 AISHELL-3 fastspeech2-aishell3 fastspeech2_nosil_aishell3_ckpt_0.4.zip
FastSpeech2 LJSpeech fastspeech2-ljspeech fastspeech2_nosil_ljspeech_ckpt_0.5.zip
FastSpeech2 VCTK fastspeech2-csmsc fastspeech2_nosil_vctk_ckpt_0.5.zip

Vocoders

Model Type Dataset Example Link Pretrained Models Static Models Size(static)
WaveFlow LJSpeech waveflow-ljspeech waveflow_ljspeech_ckpt_0.3.zip
Parallel WaveGAN CSMSC PWGAN-csmsc pwg_baker_ckpt_0.4.zip pwg_baker_static_0.4.zip 5.1MB
Parallel WaveGAN LJSpeech PWGAN-ljspeech pwg_ljspeech_ckpt_0.5.zip
Parallel WaveGAN AISHELL-3 PWGAN-aishell3 pwg_aishell3_ckpt_0.5.zip
Parallel WaveGAN VCTK PWGAN-vctk pwg_vctk_ckpt_0.5.zip
Multi Band MelGAN CSMSC MB MelGAN-csmsc mb_melgan_baker_ckpt_0.5.zip mb_melgan_baker_static_0.5.zip 8.2MB

Voice Cloning

Model Type Dataset Example Link Pretrained Models
GE2E AISHELL-3, etc. ge2e ge2e_ckpt_0.3.zip
GE2E + Tactron2 AISHELL-3 ge2e-tactron2-aishell3 tacotron2_aishell3_ckpt_0.3.zip