未验证 提交 e0280ff9 编写于 作者: P pollyyan 提交者: GitHub

Merge pull request #1431 from yt605155624/fix_dead_link

[doc]fix dead links
......@@ -10,9 +10,9 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER |
[Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 284 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.056 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1)
[Transformer Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_transformer_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 128 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0523 || 151 h | [Transformer Aishell ASR1](../../examples/aishell/asr1)
[Ds2 Offline Librispeech ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr0/asr0_deepspeech2_librispeech_ckpt_0.1.1.model.tar.gz)| Librispeech Dataset | Char-based | 518 MB | 2 Conv + 3 bidirectional LSTM layers| - |0.0725| 960 h | [Ds2 Offline Librispeech ASR0](../../examples/librispeech/asr0)
[Conformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/asr1_conformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 191 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0337 | 960 h | [Conformer Librispeech ASR1](../../example/librispeech/asr1)
[Transformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/asr1_transformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0381 | 960 h | [Transformer Librispeech ASR1](../../example/librispeech/asr1)
[Transformer Librispeech ASR2 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr2/asr2_transformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: JoinCTC w/ LM |-| 0.0240 | 960 h | [Transformer Librispeech ASR2](../../example/librispeech/asr2)
[Conformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/asr1_conformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 191 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0337 | 960 h | [Conformer Librispeech ASR1](../../examples/librispeech/asr1)
[Transformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/asr1_transformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0381 | 960 h | [Transformer Librispeech ASR1](../../examples/librispeech/asr1)
[Transformer Librispeech ASR2 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr2/asr2_transformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: JoinCTC w/ LM |-| 0.0240 | 960 h | [Transformer Librispeech ASR2](../../examples/librispeech/asr2)
### Language Model based on NGram
Language Model | Training Data | Token-based | Size | Descriptions
......@@ -66,7 +66,7 @@ GE2E + FastSpeech2 | AISHELL-3 |[ge2e-fastspeech2-aishell3](https://github.com/
Model Type | Dataset| Example Link | Pretrained Models
:-------------:| :------------:| :-----: | :-----:
PANN | Audioset| [audioset_tagging_cnn](https://github.com/qiuqiangkong/audioset_tagging_cnn) | [panns_cnn6.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn6.pdparams), [panns_cnn10.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn10.pdparams), [panns_cnn14.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn14.pdparams)
PANN | ESC-50 |[pann-esc50]("./examples/esc50/cls0")|[esc50_cnn6.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn6.tar.gz), [esc50_cnn10.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn10.tar.gz), [esc50_cnn14.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn14.tar.gz)
PANN | ESC-50 |[pann-esc50](../../examples/esc50/cls0)|[esc50_cnn6.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn6.tar.gz), [esc50_cnn10.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn10.tar.gz), [esc50_cnn14.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn14.tar.gz)
## Punctuation Restoration Models
Model Type | Dataset| Example Link | Pretrained Models
......
......@@ -71,7 +71,3 @@ Check our [website](https://paddlespeech.readthedocs.io/en/latest/tts/demo.html)
#### GE2E
1. [ge2e_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/ge2e_ckpt_0.3.zip)
## License
Parakeet is provided under the [Apache-2.0 license](LICENSE).
......@@ -27,7 +27,7 @@ cd a0
应用程序会自动下载 THCHS-30数据集,处理成 MFA 所需的文件格式并开始训练,您可以修改 `run.sh` 中的参数 `LEXICON_NAME` 来决定您需要强制对齐的级别(word、syllable 和 phone)
## MFA 所使用的字典
---
MFA 字典的格式请参考: [MFA 官方文档 Dictionary format ](https://montreal-forced-aligner.readthedocs.io/en/latest/dictionary.html)
MFA 字典的格式请参考: [MFA 官方文档](https://montreal-forced-aligner.readthedocs.io/en/latest/)
phone.lexicon 直接使用的是 `THCHS-30/data_thchs30/lm_phone/lexicon.txt`
word.lexicon 考虑到了中文的多音字,使用**带概率的字典**, 生成规则请参考 `local/gen_word2phone.py`
`syllable.lexicon` 获取自 [DNSun/thchs30-pinyin2tone](https://github.com/DNSun/thchs30-pinyin2tone)
......@@ -39,4 +39,4 @@ word.lexicon 考虑到了中文的多音字,使用**带概率的字典**, 生
**syllabel 级别:** [syllable.lexicon](https://paddlespeech.bj.bcebos.com/MFA/THCHS30/syllable/syllable.lexicon)[对齐结果](https://paddlespeech.bj.bcebos.com/MFA/THCHS30/syllable/thchs30_alignment.tar.gz)[模型](https://paddlespeech.bj.bcebos.com/MFA/THCHS30/syllable/thchs30_model.zip)
**word 级别:** [word.lexicon](https://paddlespeech.bj.bcebos.com/MFA/THCHS30/word/word.lexicon)[对齐结果](https://paddlespeech.bj.bcebos.com/MFA/THCHS30/word/thchs30_alignment.tar.gz)[模型](https://paddlespeech.bj.bcebos.com/MFA/THCHS30/word/thchs30_model.zip)
随后,您可以参考 [MFA 官方文档 Align using pretrained models](https://montreal-forced-aligner.readthedocs.io/en/stable/aligning.html#align-using-pretrained-models) 使用我们给您提供好的模型直接对自己的数据集进行强制对齐,注意,您需要使用和模型对应的 lexicon 文件,当文本是汉字时,您需要用空格把不同的**汉字**(而不是词语)分开
随后,您可以参考 [MFA 官方文档](https://montreal-forced-aligner.readthedocs.io/en/latest/) 使用我们给您提供好的模型直接对自己的数据集进行强制对齐,注意,您需要使用和模型对应的 lexicon 文件,当文本是汉字时,您需要用空格把不同的**汉字**(而不是词语)分开
### Prepare the environment
Please follow the instructions shown in [here](../../docs/source/install.md) to install the Deepspeech first.
Please follow the instructions shown in [here](../../../docs/source/install.md) to install the Deepspeech first.
### File list
└── benchmark # 模型名
......
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