def test_sick_mono(sick_dict, sick_corpus, generated_dir, mono_train_config, mono_align_model_path, mono_align_config, mono_output_directory): shutil.rmtree(sick_corpus.output_directory, ignore_errors=True) os.makedirs(sick_corpus.output_directory, exist_ok=True) mono_train_config, align_config = mono_train_config print(mono_train_config.training_configs[0].feature_config.use_mp) data_directory = os.path.join(generated_dir, 'temp', 'mono_train_test') shutil.rmtree(data_directory, ignore_errors=True) a = TrainableAligner(sick_corpus, sick_dict, mono_train_config, align_config, temp_directory=data_directory) a.train() a.save(mono_align_model_path) model = AcousticModel(mono_align_model_path) data_directory = os.path.join(generated_dir, 'temp', 'mono_align_test') shutil.rmtree(data_directory, ignore_errors=True) a = PretrainedAligner(sick_corpus, sick_dict, model, mono_align_config, temp_directory=data_directory) a.align() a.export_textgrids(mono_output_directory)
def align_corpus(args): all_begin = time.time() if not args.temp_directory: temp_dir = TEMP_DIR else: temp_dir = os.path.expanduser(args.temp_directory) corpus_name = os.path.basename(args.corpus_directory) if corpus_name == '': args.corpus_directory = os.path.dirname(args.corpus_directory) corpus_name = os.path.basename(args.corpus_directory) data_directory = os.path.join(temp_dir, corpus_name) conf_path = os.path.join(data_directory, 'config.yml') if os.path.exists(conf_path): with open(conf_path, 'r') as f: conf = yaml.load(f, Loader=yaml.SafeLoader) else: conf = {'dirty': False, 'begin': time.time(), 'version': __version__, 'type': 'align', 'corpus_directory': args.corpus_directory, 'dictionary_path': args.dictionary_path} if getattr(args, 'clean', False) \ or conf['dirty'] or conf['type'] != 'align' \ or conf['corpus_directory'] != args.corpus_directory \ or conf['version'] != __version__ \ or conf['dictionary_path'] != args.dictionary_path: shutil.rmtree(data_directory, ignore_errors=True) os.makedirs(data_directory, exist_ok=True) os.makedirs(args.output_directory, exist_ok=True) try: corpus = AlignableCorpus(args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs) if corpus.issues_check: print('WARNING: Some issues parsing the corpus were detected. ' 'Please run the validator to get more information.') print(corpus.speaker_utterance_info()) acoustic_model = AcousticModel(args.acoustic_model_path) dictionary = Dictionary(args.dictionary_path, data_directory, word_set=corpus.word_set) acoustic_model.validate(dictionary) begin = time.time() if args.config_path: align_config = align_yaml_to_config(args.config_path) else: align_config = load_basic_align() a = PretrainedAligner(corpus, dictionary, acoustic_model, align_config, temp_directory=data_directory, debug=getattr(args, 'debug', False)) if args.debug: print('Setup pretrained aligner in {} seconds'.format(time.time() - begin)) a.verbose = args.verbose begin = time.time() a.align() if args.debug: print('Performed alignment in {} seconds'.format(time.time() - begin)) begin = time.time() a.export_textgrids(args.output_directory) if args.debug: print('Exported TextGrids in {} seconds'.format(time.time() - begin)) print('Done! Everything took {} seconds'.format(time.time() - all_begin)) except Exception as _: conf['dirty'] = True raise finally: with open(conf_path, 'w') as f: yaml.dump(conf, f)
def train_ivector(args): command = 'train_ivector' all_begin = time.time() if not args.temp_directory: temp_dir = TEMP_DIR else: temp_dir = os.path.expanduser(args.temp_directory) corpus_name = os.path.basename(args.corpus_directory) if corpus_name == '': args.corpus_directory = os.path.dirname(args.corpus_directory) corpus_name = os.path.basename(args.corpus_directory) data_directory = os.path.join(temp_dir, corpus_name) if args.config_path: train_config, align_config = train_yaml_to_config(args.config_path) else: train_config, align_config = load_basic_train_ivector() conf_path = os.path.join(data_directory, 'config.yml') if getattr(args, 'clean', False) and os.path.exists(data_directory): print('Cleaning old directory!') shutil.rmtree(data_directory, ignore_errors=True) logger = setup_logger(command, data_directory) if os.path.exists(conf_path): with open(conf_path, 'r') as f: conf = yaml.load(f, Loader=yaml.SafeLoader) else: conf = { 'dirty': False, 'begin': all_begin, 'version': __version__, 'type': command, 'corpus_directory': args.corpus_directory, 'dictionary_path': args.dictionary_path, 'acoustic_model_path': args.acoustic_model_path, } if conf['dirty'] or conf['type'] != command \ or conf['corpus_directory'] != args.corpus_directory \ or conf['version'] != __version__ \ or conf['dictionary_path'] != args.dictionary_path \ or conf['acoustic_model_path'] != args.acoustic_model_path: logger.warning( 'WARNING: Using old temp directory, this might not be ideal for you, use the --clean flag to ensure no ' 'weird behavior for previous versions of the temporary directory.') if conf['dirty']: logger.debug('Previous run ended in an error (maybe ctrl-c?)') if conf['type'] != command: logger.debug( 'Previous run was a different subcommand than {} (was {})'. format(command, conf['type'])) if conf['corpus_directory'] != args.corpus_directory: logger.debug('Previous run used source directory ' 'path {} (new run: {})'.format( conf['corpus_directory'], args.corpus_directory)) if conf['version'] != __version__: logger.debug('Previous run was on {} version (new run: {})'.format( conf['version'], __version__)) if conf['dictionary_path'] != args.dictionary_path: logger.debug('Previous run used dictionary path {} ' '(new run: {})'.format(conf['dictionary_path'], args.dictionary_path)) if conf['acoustic_model_path'] != args.acoustic_model_path: logger.debug('Previous run used acoustic model path {} ' '(new run: {})'.format(conf['acoustic_model_path'], args.acoustic_model_path)) os.makedirs(data_directory, exist_ok=True) try: begin = time.time() corpus = AlignableCorpus(args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs, debug=getattr(args, 'debug', False), logger=logger, use_mp=align_config.use_mp) acoustic_model = AcousticModel(args.acoustic_model_path) dictionary = Dictionary(args.dictionary_path, data_directory, word_set=corpus.word_set, logger=logger) acoustic_model.validate(dictionary) a = PretrainedAligner(corpus, dictionary, acoustic_model, align_config, temp_directory=data_directory, logger=logger) logger.debug( 'Setup pretrained aligner in {} seconds'.format(time.time() - begin)) a.verbose = args.verbose begin = time.time() a.align() logger.debug('Performed alignment in {} seconds'.format(time.time() - begin)) for identifier, trainer in train_config.items(): trainer.logger = logger if identifier != 'ivector': continue begin = time.time() trainer.init_training(identifier, data_directory, corpus, dictionary, a) trainer.train(call_back=print) logger.debug('Training took {} seconds'.format(time.time() - begin)) trainer.save(args.output_model_path) logger.info('All done!') logger.debug('Done! Everything took {} seconds'.format(time.time() - all_begin)) except Exception as e: conf['dirty'] = True raise e finally: handlers = logger.handlers[:] for handler in handlers: handler.close() logger.removeHandler(handler) with open(conf_path, 'w') as f: yaml.dump(conf, f)
def train_dictionary(args): command = 'train_dictionary' all_begin = time.time() if not args.temp_directory: temp_dir = TEMP_DIR else: temp_dir = os.path.expanduser(args.temp_directory) corpus_name = os.path.basename(args.corpus_directory) if corpus_name == '': args.corpus_directory = os.path.dirname(args.corpus_directory) corpus_name = os.path.basename(args.corpus_directory) data_directory = os.path.join(temp_dir, corpus_name) conf_path = os.path.join(data_directory, 'config.yml') if args.config_path: align_config = align_yaml_to_config(args.config_path) else: align_config = load_basic_align() if getattr(args, 'clean', False) and os.path.exists(data_directory): print('Cleaning old directory!') shutil.rmtree(data_directory, ignore_errors=True) logger = setup_logger(command, data_directory) if os.path.exists(conf_path): with open(conf_path, 'r') as f: conf = yaml.load(f, Loader=yaml.SafeLoader) else: conf = {'dirty': False, 'begin': time.time(), 'version': __version__, 'type': command, 'corpus_directory': args.corpus_directory, 'dictionary_path': args.dictionary_path, 'acoustic_model_path': args.acoustic_model_path } if conf['dirty'] or conf['type'] != command \ or conf['corpus_directory'] != args.corpus_directory \ or conf['version'] != __version__ \ or conf['dictionary_path'] != args.dictionary_path: logger.warning( 'WARNING: Using old temp directory, this might not be ideal for you, use the --clean flag to ensure no ' 'weird behavior for previous versions of the temporary directory.') if conf['dirty']: logger.debug('Previous run ended in an error (maybe ctrl-c?)') if conf['type'] != command: logger.debug('Previous run was a different subcommand than {} (was {})'.format(command, conf['type'])) if conf['corpus_directory'] != args.corpus_directory: logger.debug('Previous run used source directory ' 'path {} (new run: {})'.format(conf['corpus_directory'], args.corpus_directory)) if conf['version'] != __version__: logger.debug('Previous run was on {} version (new run: {})'.format(conf['version'], __version__)) if conf['dictionary_path'] != args.dictionary_path: logger.debug('Previous run used dictionary path {} ' '(new run: {})'.format(conf['dictionary_path'], args.dictionary_path)) if conf['acoustic_model_path'] != args.acoustic_model_path: logger.debug('Previous run used acoustic model path {} ' '(new run: {})'.format(conf['acoustic_model_path'], args.acoustic_model_path)) os.makedirs(data_directory, exist_ok=True) try: corpus = AlignableCorpus(args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs, use_mp=align_config.use_mp, logger=logger) if corpus.issues_check: logger.warning('WARNING: Some issues parsing the corpus were detected. ' 'Please run the validator to get more information.') logger.info(corpus.speaker_utterance_info()) acoustic_model = AcousticModel(args.acoustic_model_path) dictionary = Dictionary(args.dictionary_path, data_directory, word_set=corpus.word_set, logger=logger) acoustic_model.validate(dictionary) begin = time.time() a = PretrainedAligner(corpus, dictionary, acoustic_model, align_config, temp_directory=data_directory, debug=getattr(args, 'debug', False), logger=logger) logger.debug('Setup pretrained aligner in {} seconds'.format(time.time() - begin)) a.verbose = args.verbose begin = time.time() a.align() logger.debug('Performed alignment in {} seconds'.format(time.time() - begin)) a.generate_pronunciations(args.output_directory) print('Done! Everything took {} seconds'.format(time.time() - all_begin)) except Exception as _: conf['dirty'] = True raise finally: with open(conf_path, 'w') as f: yaml.dump(conf, f)