Dev no emo (#123)
* Create emo_gen.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update server.py, fix bugs in func get_text() and infer(). (#52) * Extract get_text() and infer() from webui.py. (#53) * Extract get_text() and infer() from webui.py. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * add emo emb * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * init emo gen * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * init emo * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * init emo * Delete bert/bert-base-japanese-v3 directory * Create .gitkeep * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Create add_punc.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix bug in bert_gen.py (#54) * Update README.md * fix bug in models.py (#56) * 更新 models.py * Fix japanese cleaner (#61) * 初步，睡觉明天继续写（ * 好好好放错分支了，熬夜是大忌 * [pre-commit.ci] pre-commit autoupdate (#55) * [pre-commit.ci] pre-commit autoupdate updates: - [github.com/pre-commit/pre-commit-hooks: v4.4.0 → v4.5.0](https://github.com/pre-commit/pre-commit-hooks/compare/v4.4.0...v4.5.0) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Create tokenizer_config.json * update preprocess_text.py：过滤一个音频匹配多个文本的情况 (#57) * update preprocess_text.py：过滤音频不存在的情况 (#58) * 修复日语cleaner和bert * better * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sora <atri@suzakuintsubaki.com> * Apply Code Formatter Change * Add config.yml for global configuration. (#62) * Add config.yml for global configuration. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix bug in webui.py. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Rename config.yml to default_config.yml. Add ./config.yml to gitignore. * Add config.py to parse config.yml * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update webui.py (#65) * Update webui.py: 1. Add auto translation from Chinese to Japanese. 2. Start to use config.py in webui.py to set config instead of using the command line. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix (#68) * 加上ー * fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update infer.py and webui.py. Supports loading and inference models of 1.1.1 version. (#66) * Update infer.py and webui.py. Supports loading and inference models of 1.1.1 version. * Update config.json * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix bug in translate.py (#69) * Supports loading and inference models of 1.1、1.0.1、1.0 version. (#70) * Supports loading and inference models of 1.1、1.0.1、1.0 version. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Delete useless file in OldVersion --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update japanese.py (#71) Handling JA long pronunciations * 使用配置文件配置bert_gen.py, preprocess_text.py, resample.py (#72) * Update bert_gen.py, preprocess_text.py, resample.py. Support using config.yml in these files. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update bert_gen.py * Update bert_gen.py, fix bug. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Delete bert/bert-base-japanese-v3 directory * Create config.json * Create tokenizer_config.json * Create vocab.txt * Update server.py. 支持多版本多模型 (#76) * Update server.py. 支持多版本多模型 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Dev webui (#77) * 申请pr (#75) * 2023/10/11 update 界面优化 * Update webui.py 翻译英文页面为中文 * Update train_ms.py 单卡训练 * 加入图片 * Update extern_subprocess.py * Update asr_transcript.py * Update asr_transcript.py * Update asr_transcript.py * Update extern_subprocess.py * Update asr_transcript.py * Update asr_transcript.py * Update asr_transcript.py * Update all_process.py * Update extern_subprocess.py * Update all_process.py * Update all_process.py * Update asr_transcript.py * Update extern_subprocess.py * Update webui.py * Create re_matching.py * Update webui.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update all_process.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update all_process.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update all_process.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update asr_transcript.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Pack 'update' functions into a module * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update all_process.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update asr_transcript.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update extern_subprocess.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update all_process.py * Update asr_transcript.py * Update webui.py * Add files via upload * Update extern_subprocess.py * Update all_process.py * Update asr_transcript.py * Update bert_gen.py * Update extern_subprocess.py * Update preprocess_text.py * Update re_matching.py * Update resample.py * Update update_status.py * Update update_status.py * Update webui.py * Update all_process.py * Update preprocess_text.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update train_ms.py --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> Co-authored-by: innnky <67028263+innnky@users.noreply.github.com> * Delete all_process.py * Delete asr_transcript.py * Delete extern_subprocess.py --------- Co-authored-by: spicysama <122108331+AnyaCoder@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: innnky <67028263+innnky@users.noreply.github.com> * Create config.json * Create preprocessor_config.json * Create vocab.json * Delete emotional/wav2vec2-large-robust-12-ft-emotion-msp-dim/.gitkeep * Update emo_gen.py * Delete add_punc.py * add emotion_clustering.i * Apply Code Formatter Change * Update models.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update preprocess_text.py (#78) * Update preprocess_text.py. 检测重复以及不存在的音频 (#79) * Handle Janpanese long pronunciations (#80) * Handle Janpanese long pronunciations * Update japanese.py * Update japanese.py * Use unified phonemes for Japanese long vowel (#82) * Use an unified phoneme for Japanese long vowel `symbol.py` has not been updated to ensure compatibility with older version models. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * 增加一个按钮，点击后可以按句子切分，添加“|” (#81) * Update re_matching.py * Update webui.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix phonemer bug (#83) * Fix phonemer bug * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix long vowel handler bug (#84) * Fix long vowel handler bug * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * 加入整合包管理器的特性：长文本合成可以自定义句间段间停顿 (#85) * Update webui.py * Update re_matching.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update train_ms.py * fix' * Update cleaner.py * add en * add en * Update english.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add en * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add en * add en * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add en * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * 更新 README.md * 更新 README.md * 更新 README.md * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Change phonemer to pyopenjtalk (#86) * Change phonemer to pyopenjtalk * 修改为openjtalk便于安装 --------- Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> * 更新 english.py * Fix english_bert_mock.py. (#87) * Add punctuation execptions (#88) * Add punctuation execptions * Ellipses exceptions * remove get bert * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix bug in oldVersion. (#89) * Update requirements.txt * change to large * rollback requirements.txt * Feat: Enable 1.1.1 models using fix-ver infer. (#91) * Feat: Enable 1.1.1 models using fix-ver infer. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Add Japanese accent (high-low) (#90) * Add punctuation execptions * Ellipses exceptions * Add Japanese accent * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Do not replace iteration mark (#92) * Add punctuation execptions * Ellipses exceptions * Add Japanese accent * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Do not replace iteration mark --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix: fix import error in oldVersion (#93) * Refactor: reusing model loading in webui.py and server.py. (#94) * Feat: Enable using config.yml in train_ms.py (#96) * 更新 emo_gen.py * Change emo_gen.py (#97) * Fix emo_gen bugs * Add multiprocess * Fix queue (#98) * Fix emo_gen bugs * Add multiprocess * Del var * Fix queue * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix training bugs (#99) * Updatge cluster notebook * Fix train * Fix filename * Update infer.py (#100) * Update infer.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Add reference audio (#101) * Add reference audio * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update * Update * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> * Fix: fix 1.1.1-fix (#102) * Fix infer bug (#103) * Feat: Add server_fastapi.py. (#104) * Feat: Add server_fastapi.py. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix: Update requirements.txt. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix: requirements.txt. (#105) * Swith to deberta-v3-large (#106) * Swith to deberta-v3-large * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Feat: Update config.py. (#107) * Feat: Update config.py. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Dev fix (#108) * fix bugs when deploying * fix bugs when deploying * fix bugs when deploying * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Revert "Dev fix (#108)" (#109) This reverts commit 685e18a10498d602b1a9a26079340d11925646f0. * Dev fix (#110) * fix bugs when deploying * fix bugs when deploying * fix bugs when deploying * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix fixed bugs * fix fixed bugs * fix fixed bug 3 * fix fixed bug 4 * fix fixed bug 5 * fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Add emo vec quantizer (#111) Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> * Clean req and gitignore (#112) * Clean req and gitignore * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Switch to deberta-v2-large-japanese (#113) * Switch to deberta-v2-large-japanese * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix emo bugs (#114) * Fix english (#115) * Remove emo (#117) * Don't train codebook * Remove emo * Update * Update * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Merge dev into no-emo (#122) * [pre-commit.ci] pre-commit autoupdate (#95) * [pre-commit.ci] pre-commit autoupdate updates: - [github.com/astral-sh/ruff-pre-commit: v0.0.292 → v0.1.1](https://github.com/astral-sh/ruff-pre-commit/compare/v0.0.292...v0.1.1) - [github.com/psf/black: 23.9.1 → 23.10.0](https://github.com/psf/black/compare/23.9.1...23.10.0) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Don't train codebook (#116) * Update requirements.txt * Update english_bert_mock.py * Fix: server_fastapi.py (#118) * Fix: server_fastapi.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix: don't print debug logging. (#119) * Fix: don't print debug logging. * Feat: support emo_gen config * Fix config * Apply Code Formatter Change * 更新，修正bug (#121) * Feat: Update infer.py preprocess_text.py server_fastapi.py. * Fix resample.py. Maintain same directory structure in out_dir as in_dir. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update resample.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update server_fastapi.py to no-emo ver * Update config.py, no emo config --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: OedoSoldier <31711261+OedoSoldier@users.noreply.github.com> Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> Co-authored-by: Stardust-minus <Stardust-minus@users.noreply.github.com> * Update train_ms.py * Update latest version info (#124) --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: jiangyuxiaoxiao <atri@suzakuintsubaki.com> Co-authored-by: AkitoLiu <39857739+Akito-UzukiP@users.noreply.github.com> Co-authored-by: Stardust-minus <Stardust-minus@users.noreply.github.com> Co-authored-by: OedoSoldier <31711261+OedoSoldier@users.noreply.github.com> Co-authored-by: spicysama <122108331+AnyaCoder@users.noreply.github.com> Co-authored-by: innnky <67028263+innnky@users.noreply.github.com> Co-authored-by: YYuX-1145 <138500330+YYuX-1145@users.noreply.github.com>
This commit is contained in:
Stardust·减
162
text/english.py
162
text/english.py
@@ -171,22 +171,160 @@ def refine_syllables(syllables):
|
||||
return phonemes, tones
|
||||
|
||||
|
||||
import re
|
||||
import inflect
|
||||
|
||||
_inflect = inflect.engine()
|
||||
_comma_number_re = re.compile(r"([0-9][0-9\,]+[0-9])")
|
||||
_decimal_number_re = re.compile(r"([0-9]+\.[0-9]+)")
|
||||
_pounds_re = re.compile(r"£([0-9\,]*[0-9]+)")
|
||||
_dollars_re = re.compile(r"\$([0-9\.\,]*[0-9]+)")
|
||||
_ordinal_re = re.compile(r"[0-9]+(st|nd|rd|th)")
|
||||
_number_re = re.compile(r"[0-9]+")
|
||||
|
||||
# List of (regular expression, replacement) pairs for abbreviations:
|
||||
_abbreviations = [
|
||||
(re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
|
||||
for x in [
|
||||
("mrs", "misess"),
|
||||
("mr", "mister"),
|
||||
("dr", "doctor"),
|
||||
("st", "saint"),
|
||||
("co", "company"),
|
||||
("jr", "junior"),
|
||||
("maj", "major"),
|
||||
("gen", "general"),
|
||||
("drs", "doctors"),
|
||||
("rev", "reverend"),
|
||||
("lt", "lieutenant"),
|
||||
("hon", "honorable"),
|
||||
("sgt", "sergeant"),
|
||||
("capt", "captain"),
|
||||
("esq", "esquire"),
|
||||
("ltd", "limited"),
|
||||
("col", "colonel"),
|
||||
("ft", "fort"),
|
||||
]
|
||||
]
|
||||
|
||||
|
||||
# List of (ipa, lazy ipa) pairs:
|
||||
_lazy_ipa = [
|
||||
(re.compile("%s" % x[0]), x[1])
|
||||
for x in [
|
||||
("r", "ɹ"),
|
||||
("æ", "e"),
|
||||
("ɑ", "a"),
|
||||
("ɔ", "o"),
|
||||
("ð", "z"),
|
||||
("θ", "s"),
|
||||
("ɛ", "e"),
|
||||
("ɪ", "i"),
|
||||
("ʊ", "u"),
|
||||
("ʒ", "ʥ"),
|
||||
("ʤ", "ʥ"),
|
||||
("ˈ", "↓"),
|
||||
]
|
||||
]
|
||||
|
||||
# List of (ipa, lazy ipa2) pairs:
|
||||
_lazy_ipa2 = [
|
||||
(re.compile("%s" % x[0]), x[1])
|
||||
for x in [
|
||||
("r", "ɹ"),
|
||||
("ð", "z"),
|
||||
("θ", "s"),
|
||||
("ʒ", "ʑ"),
|
||||
("ʤ", "dʑ"),
|
||||
("ˈ", "↓"),
|
||||
]
|
||||
]
|
||||
|
||||
# List of (ipa, ipa2) pairs
|
||||
_ipa_to_ipa2 = [
|
||||
(re.compile("%s" % x[0]), x[1]) for x in [("r", "ɹ"), ("ʤ", "dʒ"), ("ʧ", "tʃ")]
|
||||
]
|
||||
|
||||
|
||||
def _expand_dollars(m):
|
||||
match = m.group(1)
|
||||
parts = match.split(".")
|
||||
if len(parts) > 2:
|
||||
return match + " dollars" # Unexpected format
|
||||
dollars = int(parts[0]) if parts[0] else 0
|
||||
cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
|
||||
if dollars and cents:
|
||||
dollar_unit = "dollar" if dollars == 1 else "dollars"
|
||||
cent_unit = "cent" if cents == 1 else "cents"
|
||||
return "%s %s, %s %s" % (dollars, dollar_unit, cents, cent_unit)
|
||||
elif dollars:
|
||||
dollar_unit = "dollar" if dollars == 1 else "dollars"
|
||||
return "%s %s" % (dollars, dollar_unit)
|
||||
elif cents:
|
||||
cent_unit = "cent" if cents == 1 else "cents"
|
||||
return "%s %s" % (cents, cent_unit)
|
||||
else:
|
||||
return "zero dollars"
|
||||
|
||||
|
||||
def _remove_commas(m):
|
||||
return m.group(1).replace(",", "")
|
||||
|
||||
|
||||
def _expand_ordinal(m):
|
||||
return _inflect.number_to_words(m.group(0))
|
||||
|
||||
|
||||
def _expand_number(m):
|
||||
num = int(m.group(0))
|
||||
if num > 1000 and num < 3000:
|
||||
if num == 2000:
|
||||
return "two thousand"
|
||||
elif num > 2000 and num < 2010:
|
||||
return "two thousand " + _inflect.number_to_words(num % 100)
|
||||
elif num % 100 == 0:
|
||||
return _inflect.number_to_words(num // 100) + " hundred"
|
||||
else:
|
||||
return _inflect.number_to_words(
|
||||
num, andword="", zero="oh", group=2
|
||||
).replace(", ", " ")
|
||||
else:
|
||||
return _inflect.number_to_words(num, andword="")
|
||||
|
||||
|
||||
def _expand_decimal_point(m):
|
||||
return m.group(1).replace(".", " point ")
|
||||
|
||||
|
||||
def normalize_numbers(text):
|
||||
text = re.sub(_comma_number_re, _remove_commas, text)
|
||||
text = re.sub(_pounds_re, r"\1 pounds", text)
|
||||
text = re.sub(_dollars_re, _expand_dollars, text)
|
||||
text = re.sub(_decimal_number_re, _expand_decimal_point, text)
|
||||
text = re.sub(_ordinal_re, _expand_ordinal, text)
|
||||
text = re.sub(_number_re, _expand_number, text)
|
||||
return text
|
||||
|
||||
|
||||
def text_normalize(text):
|
||||
# todo: eng text normalize
|
||||
text = normalize_numbers(text)
|
||||
return text
|
||||
|
||||
|
||||
def g2p(text):
|
||||
phones = []
|
||||
tones = []
|
||||
word2ph = []
|
||||
words = re.split(r"([,;.\-\?\!\s+])", text)
|
||||
for w in words:
|
||||
if w.upper() in eng_dict:
|
||||
phns, tns = refine_syllables(eng_dict[w.upper()])
|
||||
words = [word for word in words if word.strip() != ""]
|
||||
for word in words:
|
||||
if word.upper() in eng_dict:
|
||||
phns, tns = refine_syllables(eng_dict[word.upper()])
|
||||
phones += phns
|
||||
tones += tns
|
||||
word2ph.append(len(phns))
|
||||
else:
|
||||
phone_list = list(filter(lambda p: p != " ", _g2p(w)))
|
||||
phone_list = list(filter(lambda p: p != " ", _g2p(word)))
|
||||
for ph in phone_list:
|
||||
if ph in arpa:
|
||||
ph, tn = refine_ph(ph)
|
||||
@@ -195,13 +333,23 @@ def g2p(text):
|
||||
else:
|
||||
phones.append(ph)
|
||||
tones.append(0)
|
||||
# todo: implement word2ph
|
||||
word2ph = [1 for i in phones]
|
||||
word2ph.append(len(phone_list))
|
||||
|
||||
phones = [post_replace_ph(i) for i in phones]
|
||||
|
||||
phones = ["_"] + phones + ["_"]
|
||||
tones = [0] + tones + [0]
|
||||
word2ph = [1] + word2ph + [1]
|
||||
|
||||
return phones, tones, word2ph
|
||||
|
||||
|
||||
def get_bert_feature(text, word2ph):
|
||||
from text import english_bert_mock
|
||||
|
||||
return english_bert_mock.get_bert_feature(text, word2ph)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# print(get_dict())
|
||||
# print(eng_word_to_phoneme("hello"))
|
||||
|
||||
Reference in New Issue
Block a user