提交 396db4a5 编写于 作者: H Hui Zhang

update librispeech asr1-2 result; add warpctc source link in ctc topic

上级 b6ade97b
# 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 | example link
:-------------:| :------------:| :-----: | -----: | :----------------- |:--------- | :---------- | :--------- | :-----------
......@@ -9,8 +10,9 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER |
[Conformer Online Aishell ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.chunk.release.tar.gz) | Aishell Dataset | Char-based | 283 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0594 |-| 151 h | [Conformer Online Aishell S1 Example](../../examples/aishell/s1)
[Conformer Offline Aishell ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.release.tar.gz) | Aishell Dataset | Char-based | 284 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0547 |-| 151 h | [Conformer Offline Aishell S1 Example](../../examples/aishell/s1)
[Conformer Librispeech ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/librispeech/s1/conformer.release.tar.gz) | Librispeech Dataset | subword-based | 287 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0325 | 960 h | [Conformer Librispeech S1 example](../../example/librispeech/s1)
[Transformer Librispeech ASR1 Model](https://deepspeech.bj.bcebos.com/release2.2/librispeech/s1/librispeech.s1.transformer.all.wer5p62.release.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0456 | 960 h | [Transformer Librispeech S1 example](../../example/librispeech/s1)
[Transformer Librispeech ASR2 Model](https://deepspeech.bj.bcebos.com/release2.2/librispeech/s2/libri_transformer_espnet_wer3p84.release.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention |-| 0.0384 | 960 h | [Transformer Librispeech S2 example](../../example/librispeech/s2)
[Transformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/transformer.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0410 | 960 h | [Transformer Librispeech S1 example](../../example/librispeech/s1)
[Transformer Librispeech ASR2 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr2/transformer.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: JoinCTC w/ LM |-| 0.024 | 960 h | [Transformer Librispeech S2 example](../../example/librispeech/s2)
### Acoustic Model Transformed from paddle 1.8
Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech
......@@ -20,14 +22,15 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER |
[Ds2 Offline Baidu en8k model](https://deepspeech.bj.bcebos.com/eng_models/baidu_en8k_v1.8_to_v2.x.tar.gz)|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](https://deepspeech.bj.bcebos.com/en_lm/common_crawl_00.prune01111.trie.klm) | [CommonCrawl(en.00)](http://web-language-models.s3-website-us-east-1.amazonaws.com/ngrams/en/deduped/en.00.deduped.xz) | Word-based | 8.3 GB | Pruned with 0 1 1 1 1; <br/> About 1.85 billion n-grams; <br/> 'trie' binary with '-a 22 -q 8 -b 8'
[Mandarin LM Small](https://deepspeech.bj.bcebos.com/zh_lm/zh_giga.no_cna_cmn.prune01244.klm) | Baidu Internal Corpus | Char-based | 2.8 GB | Pruned with 0 1 2 4 4; <br/> About 0.13 billion n-grams; <br/> 'probing' binary with default settings
[Mandarin LM Large](https://deepspeech.bj.bcebos.com/zh_lm/zhidao_giga.klm) | Baidu Internal Corpus | Char-based | 70.4 GB | No Pruning; <br/> About 3.7 billion n-grams; <br/> 'probing' binary with default settings
## Text-to-Speech Models
### Acoustic Models
Model Type | Dataset| Example Link | Pretrained Models|Static Models|Siize(static)
:-------------:| :------------:| :-----: | :-----:| :-----:| :-----:
......@@ -40,7 +43,6 @@ FastSpeech2| LJSpeech |[fastspeech2-ljspeech](https://github.com/PaddlePaddle/Pa
FastSpeech2| VCTK |[fastspeech2-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/vctk/tts3)|[fastspeech2_nosil_vctk_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_vctk_ckpt_0.5.zip)|||
### Vocoders
Model Type | Dataset| Example Link | Pretrained Models| Static Models|Size(static)
:-------------:| :------------:| :-----: | :-----:| :-----:| :-----:
WaveFlow| LJSpeech |[waveflow-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/voc0)|[waveflow_ljspeech_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/waveflow/waveflow_ljspeech_ckpt_0.3.zip)|||
......
......@@ -343,6 +343,16 @@
" $$"
]
},
{
"cell_type": "markdown",
"id": "41637c03",
"metadata": {},
"source": [
"## Source Code\n",
"本人在 [warp-ctc](https://github.com/zh794390558/warp-ctc) 上加了注释,并调整 index 的索引方式,便于理解代码。\n",
"对比上面的公式推导和lattice图可以快速理解 ctc 实现。"
]
},
{
"cell_type": "markdown",
"id": "coordinated-music",
......@@ -372,7 +382,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
......@@ -386,7 +396,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.7.0"
},
"toc": {
"base_numbering": 1,
......
......@@ -21,7 +21,7 @@
## Transformer
| Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER |
| --- | --- | --- | --- | --- | --- | --- | --- |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention | 6.733129533131917 | 0.047874 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_greedy_search | 6.733129533131917 | 0.053922 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_prefix_beam_search | 6.733129533131917 | 0.053427 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention_rescoring | 6.733129533131917 | 0.041369 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention | 6.725063021977743 | 0.047417 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_greedy_search | 6.725063021977743 | 0.053922 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_prefix_beam_search | 6.725063021977743 | 0.053180 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention_rescoring | 6.725063021977743 | 0.041026 |
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册