diff --git a/README.md b/README.md index a2de1783a62f2332349d57c1a585ff1ac3156d79..424dc485e180e3c83a507d5c9c68594bdb6055c1 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ ## Features - See [feature list](doc/src/feature_list.md) for more information. + See [feature list](doc/src/feature_list.md) for more information. ## Setup diff --git a/deepspeech/frontend/normalizer.py b/deepspeech/frontend/normalizer.py index 6b224080b958a341a23ccf71d9883f854b60bbc5..287b51e587c29d133fd56a31a3925954fb99fff5 100644 --- a/deepspeech/frontend/normalizer.py +++ b/deepspeech/frontend/normalizer.py @@ -179,7 +179,8 @@ class FeatureNormalizer(object): wav_number += batch_size if wav_number % 1000 == 0: - logger.info(f'process {wav_number} wavs,{all_number} frames.') + logger.info( + f'process {wav_number} wavs,{all_number} frames.') self.cmvn_info = { 'mean_stat': list(all_mean_stat.tolist()), diff --git a/doc/src/asr_text_backend.md b/doc/src/asr_text_backend.md index 879e56f8aadb0429ccee82365fc49be4eb21e269..c3c9896c72803951e5a4286e22053a208ad4f018 100644 --- a/doc/src/asr_text_backend.md +++ b/doc/src/asr_text_backend.md @@ -98,4 +98,4 @@ ## Text Filter -* 敏感词（黄暴、涉政、违法违禁等） \ No newline at end of file +* 敏感词（黄暴、涉政、违法违禁等） diff --git a/doc/src/benchmark.md b/doc/src/benchmark.md index f3af255524952f7c06217f5a8b4959d0ce59cf24..9c1c86fd7a83b5ae09f4dd4d5a95f5859a96845c 100644 --- a/doc/src/benchmark.md +++ b/doc/src/benchmark.md @@ -14,4 +14,3 @@ We compare the training time with 1, 2, 4, 8 Tesla V100 GPUs (with a subset of L | 8 | 6.95 X | `utils/profile.sh` provides such a demo profiling tool, you can change it as need. - diff --git a/doc/src/chinese_syllable.md b/doc/src/chinese_syllable.md index 676ecb531f025ab89fbff7c6b1ea2d6f00707114..fd5a6159a9bb45ddf2af25392e687f8e8703b6e8 100644 --- a/doc/src/chinese_syllable.md +++ b/doc/src/chinese_syllable.md @@ -48,4 +48,4 @@ ## Zhuyin * [Bopomofo](https://en.wikipedia.org/wiki/Bopomofo) -* [Zhuyin table](https://en.wikipedia.org/wiki/Zhuyin_table) \ No newline at end of file +* [Zhuyin table](https://en.wikipedia.org/wiki/Zhuyin_table) diff --git a/doc/src/dataset.md b/doc/src/dataset.md index d70d0e0d228b499fa07ea580ecf0650709cd4945..aaa805510bd8d53950afbccccf829ac680c07366 100644 --- a/doc/src/dataset.md +++ b/doc/src/dataset.md @@ -18,4 +18,4 @@ ### ASR Noise -* [asr-noises](https://github.com/speechio/asr-noises) \ No newline at end of file +* [asr-noises](https://github.com/speechio/asr-noises) diff --git a/doc/src/feature_list.md b/doc/src/feature_list.md index 57641d5eab9d4faf951b480b3dcdffd154664706..573669fa2fd6d994d5a9f3dfa69a3bbdf819b9fe 100644 --- a/doc/src/feature_list.md +++ b/doc/src/feature_list.md @@ -58,4 +58,4 @@ ### Grapheme To Phoneme * syallable -* phoneme \ No newline at end of file +* phoneme diff --git a/doc/src/ngram_lm.md b/doc/src/ngram_lm.md index 07aa5411cc710792f6985d37c712752f1c6c8036..119a3b21ccad01d12f987e679923940ebbefb64f 100644 --- a/doc/src/ngram_lm.md +++ b/doc/src/ngram_lm.md @@ -83,4 +83,4 @@ Please notice that the released language models only contain Chinese simplified ``` build/bin/build_binary ./result/people2014corpus_words.arps ./result/people2014corpus_words.klm - ``` \ No newline at end of file + ``` diff --git a/doc/src/praat_textgrid.md b/doc/src/praat_textgrid.md index c25c760ae63830c2c9c5dbbc92e4c1ce005ed040..06c4f8791a3b9576cd22e117155a78f9f84b3196 100644 --- a/doc/src/praat_textgrid.md +++ b/doc/src/praat_textgrid.md @@ -76,7 +76,7 @@ pip3 install textgrid tg.read('file.TextGrid') # 'file.TextGrid' 是文件名 ``` - tg.tiers属性: + tg.tiers属性: 会把文件中的所有item打印出来, print(tg.tiers) 的结果如下: ```text @@ -86,7 +86,7 @@ pip3 install textgrid Interval(1361.89250, 1362.01250, R), Interval(1362.01250, 1362.13250, AY1), Interval(1362.13250, 1362.16250, T), - + ... ] ) @@ -113,7 +113,7 @@ pip3 install textgrid Interval 可以理解为时长 ``` - + 2. textgrid库中的对象 **IntervalTier** 对象: @@ -148,7 +148,7 @@ pip3 install textgrid strict -- > 返回bool值, 表示是否严格TextGrid格式 ``` - ​ + ​ **PointTier** 对象: 方法 @@ -174,7 +174,7 @@ pip3 install textgrid name 返回name ``` - + **Point** 对象: 支持比较大小, 支持加减运算 @@ -185,7 +185,7 @@ pip3 install textgrid time: ``` - ​ + ​ **Interval** 对象: 支持比较大小, 支持加减运算 @@ -250,10 +250,9 @@ pip3 install textgrid grids: --> 返回读取的grids的列表 ``` - + ## Reference * https://zh.wikipedia.org/wiki/Praat%E8%AF%AD%E9%9F%B3%E5%AD%A6%E8%BD%AF%E4%BB%B6 * https://blog.csdn.net/duxin_csdn/article/details/88966295 - diff --git a/doc/src/tools.md b/doc/src/tools.md index 4ec09f6a2800dbc5e4cac310be33180f613be550..5fcca9239ee4ac87988a48b410daae75522ed231 100644 --- a/doc/src/tools.md +++ b/doc/src/tools.md @@ -1,4 +1,3 @@ # Useful Tools * [正则可视化和常用正则表达式](https://wangwl.net/static/projects/visualRegex/#) - diff --git a/doc/src/tts_text_front_end.md b/doc/src/tts_text_front_end.md index 6eb9ae5d9dacd769a02835c36134847db22fc809..9f2f91097308928a12e1c4a6b5e9546fbafd6623 100644 --- a/doc/src/tts_text_front_end.md +++ b/doc/src/tts_text_front_end.md @@ -23,7 +23,7 @@ Therefore, procedures like stemming and lemmatization are not useful for Chinese ### Tokenization -**Tokenizing breaks up text data into shorter pre-set strings**, which help build context and meaning for the machine learning model. +**Tokenizing breaks up text data into shorter pre-set strings**, which help build context and meaning for the machine learning model. These “tags” label the part of speech. There are 24 part of speech tags and 4 proper name category labels in the `**jieba**` package’s existing dictionary. @@ -31,7 +31,7 @@ These “tags” label the part of speech. There are 24 part of speech tags and ### Stop Words -In NLP, **stop words are “meaningless” words** that make the data too noisy or ambiguous. +In NLP, **stop words are “meaningless” words** that make the data too noisy or ambiguous. Instead of manually removing them, you could import the `**stopwordsiso**` package for a full list of Chinese stop words. More information can be found [here](https://pypi.org/project/stopwordsiso/). And with this, we can easily create code to filter out any stop words in large text data. @@ -188,4 +188,4 @@ TN: 基于规则的方法 ## Reference * [Text Front End](https://slyne.github.io/%E5%85%AC%E5%BC%80%E8%AF%BE/2020/10/03/TTS1/) * [Chinese Natural Language (Pre)processing: An Introduction](https://towardsdatascience.com/chinese-natural-language-pre-processing-an-introduction-995d16c2705f) -* [Beginner’s Guide to Sentiment Analysis for Simplified Chinese using SnowNLP](https://towardsdatascience.com/beginners-guide-to-sentiment-analysis-for-simplified-chinese-using-snownlp-ce88a8407efb) \ No newline at end of file +* [Beginner’s Guide to Sentiment Analysis for Simplified Chinese using SnowNLP](https://towardsdatascience.com/beginners-guide-to-sentiment-analysis-for-simplified-chinese-using-snownlp-ce88a8407efb) diff --git a/requirements.txt b/requirements.txt index a6facb6cbc86f29fd7c731aacc423f2d8b3bffb6..57a951bbd517797fc0c6685a7b7da6c4604fe975 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,6 @@ coverage pre-commit +pybind11 resampy==0.2.2 scipy==1.2.1 sentencepiece @@ -7,7 +8,6 @@ snakeviz SoundFile==0.9.0.post1 sox tensorboardX +textgrid typeguard yacs -pybind11 -textgrid