def align_corpus(corpus_dir, dict_path, output_directory, temp_dir, output_model_path, args): if temp_dir == '': temp_dir = TEMP_DIR else: temp_dir = os.path.expanduser(temp_dir) corpus_name = os.path.basename(corpus_dir) if corpus_name == '': corpus_dir = os.path.dirname(corpus_dir) corpus_name = os.path.basename(corpus_dir) data_directory = os.path.join(temp_dir, corpus_name) if args.clean: shutil.rmtree(data_directory, ignore_errors=True) shutil.rmtree(output_directory, ignore_errors=True) os.makedirs(data_directory, exist_ok=True) os.makedirs(output_directory, exist_ok=True) dictionary = Dictionary(dict_path, data_directory) dictionary.write() corpus = Corpus(corpus_dir, data_directory, args.speaker_characters, num_jobs=args.num_jobs) print(corpus.speaker_utterance_info()) corpus.write() corpus.create_mfccs() corpus.setup_splits(dictionary) utt_oov_path = os.path.join(corpus.split_directory, 'utterance_oovs.txt') if os.path.exists(utt_oov_path): shutil.copy(utt_oov_path, output_directory) oov_path = os.path.join(corpus.split_directory, 'oovs_found.txt') if os.path.exists(oov_path): shutil.copy(oov_path, output_directory) mono_params = {'align_often': not args.fast} tri_params = {'align_often': not args.fast} tri_fmllr_params = {'align_often': not args.fast} a = TrainableAligner(corpus, dictionary, output_directory, temp_directory=data_directory, mono_params=mono_params, tri_params=tri_params, tri_fmllr_params=tri_fmllr_params, num_jobs=args.num_jobs) a.verbose = args.verbose a.train_mono() a.export_textgrids() a.train_tri() a.export_textgrids() a.train_tri_fmllr() a.export_textgrids() if output_model_path is not None: a.save(output_model_path)
def align_corpus(model_path, corpus_dir, output_directory, temp_dir, args, debug = False): all_begin = time.time() if temp_dir == '': temp_dir = TEMP_DIR else: temp_dir = os.path.expanduser(temp_dir) corpus_name = os.path.basename(corpus_dir) if corpus_name == '': corpus_dir = os.path.dirname(corpus_dir) corpus_name = os.path.basename(corpus_dir) data_directory = os.path.join(temp_dir, corpus_name) if args.clean: shutil.rmtree(data_directory, ignore_errors = True) shutil.rmtree(output_directory, ignore_errors = True) os.makedirs(data_directory, exist_ok = True) os.makedirs(output_directory, exist_ok = True) begin = time.time() corpus = Corpus(corpus_dir, data_directory, args.speaker_characters, num_jobs = args.num_jobs) print(corpus.speaker_utterance_info()) corpus.write() if debug: print('Wrote corpus information in {} seconds'.format(time.time() - begin)) begin = time.time() corpus.create_mfccs() if debug: print('Calculated mfccs in {} seconds'.format(time.time() - begin)) archive = Archive(model_path) begin = time.time() a = PretrainedAligner(archive, corpus, output_directory, temp_directory = data_directory, num_jobs = args.num_jobs, speaker_independent = args.no_speaker_adaptation) if debug: print('Setup pretrained aligner in {} seconds'.format(time.time() - begin)) a.verbose = args.verbose begin = time.time() corpus.setup_splits(a.dictionary) if debug: print('Setup splits in {} seconds'.format(time.time() - begin)) utt_oov_path = os.path.join(corpus.split_directory, 'utterance_oovs.txt') if os.path.exists(utt_oov_path): shutil.copy(utt_oov_path, output_directory) oov_path = os.path.join(corpus.split_directory, 'oovs_found.txt') if os.path.exists(oov_path): shutil.copy(oov_path, output_directory) begin = time.time() a.do_align() if debug: print('Performed alignment in {} seconds'.format(time.time() - begin)) begin = time.time() a.export_textgrids() if debug: print('Exported textgrids in {} seconds'.format(time.time() - begin)) print('Done! Everything took {} seconds'.format(time.time() - all_begin))
def align_corpus(corpus_dir, dict_path, output_directory, temp_dir, output_model_path, args): if temp_dir == '': temp_dir = TEMP_DIR else: temp_dir = os.path.expanduser(temp_dir) corpus_name = os.path.basename(corpus_dir) if corpus_name == '': corpus_dir = os.path.dirname(corpus_dir) corpus_name = os.path.basename(corpus_dir) data_directory = os.path.join(temp_dir, corpus_name) if args.clean: shutil.rmtree(data_directory, ignore_errors = True) shutil.rmtree(output_directory, ignore_errors = True) os.makedirs(data_directory, exist_ok = True) os.makedirs(output_directory, exist_ok = True) corpus = Corpus(corpus_dir, data_directory, args.speaker_characters, num_jobs = args.num_jobs) print(corpus.speaker_utterance_info()) corpus.write() corpus.create_mfccs() dictionary = Dictionary(dict_path, data_directory, word_set=corpus.word_set) dictionary.write() corpus.setup_splits(dictionary) utt_oov_path = os.path.join(corpus.split_directory, 'utterance_oovs.txt') if os.path.exists(utt_oov_path): shutil.copy(utt_oov_path, output_directory) oov_path = os.path.join(corpus.split_directory, 'oovs_found.txt') if os.path.exists(oov_path): shutil.copy(oov_path, output_directory) mono_params = {'align_often': not args.fast} tri_params = {'align_often': not args.fast} tri_fmllr_params = {'align_often': not args.fast} a = TrainableAligner(corpus, dictionary, output_directory, temp_directory = data_directory, mono_params = mono_params, tri_params = tri_params, tri_fmllr_params = tri_fmllr_params, num_jobs = args.num_jobs) a.verbose = args.verbose a.train_mono() a.export_textgrids() a.train_tri() a.export_textgrids() a.train_tri_fmllr() a.export_textgrids() if output_model_path is not None: a.save(output_model_path)
def align_corpus_no_dict(args): 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) data_directory = os.path.join(temp_dir, corpus_name) if args.clean: shutil.rmtree(data_directory, ignore_errors=True) shutil.rmtree(args.output_directory, ignore_errors=True) os.makedirs(data_directory, exist_ok=True) os.makedirs(args.output_directory, exist_ok=True) corpus = Corpus(args.corpus_directory, data_directory, args.speaker_characters, num_jobs=getattr(args, 'num_jobs', 3), debug=getattr(args, 'debug', False), ignore_exceptions=getattr(args, 'ignore_exceptions', False)) print(corpus.speaker_utterance_info()) dictionary = no_dictionary(corpus, data_directory) mono_params = {'align_often': not args.fast} tri_params = {'align_often': not args.fast} tri_fmllr_params = {'align_often': not args.fast} a = TrainableAligner(corpus, dictionary, args.output_directory, temp_directory=data_directory, mono_params=mono_params, tri_params=tri_params, tri_fmllr_params=tri_fmllr_params, num_jobs=args.num_jobs, debug=args.debug, skip_input=getattr(args, 'quiet', False)) a.verbose = args.verbose a.train_mono() a.export_textgrids() a.train_tri() a.export_textgrids() a.train_tri_fmllr() a.export_textgrids() if args.output_model_path is not None: a.save(args.output_model_path)
def align_corpus(args, skip_input=False): 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) 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) shutil.rmtree(args.output_directory, ignore_errors=True) os.makedirs(data_directory, exist_ok=True) os.makedirs(args.output_directory, exist_ok=True) use_speaker_info = not args.no_speaker_adaptation try: corpus = Corpus(args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs, use_speaker_information=use_speaker_info, ignore_exceptions=getattr(args, 'ignore_exceptions', False)) 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() a = PretrainedAligner(corpus, dictionary, acoustic_model, args.output_directory, temp_directory=data_directory, num_jobs=getattr(args, 'num_jobs', 3), speaker_independent=getattr(args, 'no_speaker_adaptation', False), debug=getattr(args, 'debug', False)) if getattr(args, 'errors', False): check = a.test_utterance_transcriptions() if not skip_input and not check: user_input = input('Would you like to abort to fix transcription issues? (Y/N)') if user_input.lower() == 'y': return if args.debug: print('Setup pretrained aligner in {} seconds'.format(time.time() - begin)) a.verbose = args.verbose utt_oov_path = os.path.join(corpus.split_directory, 'utterance_oovs.txt') if os.path.exists(utt_oov_path): shutil.copy(utt_oov_path, args.output_directory) oov_path = os.path.join(corpus.split_directory, 'oovs_found.txt') if os.path.exists(oov_path): shutil.copy(oov_path, args.output_directory) if not skip_input and a.dictionary.oovs_found: user_input = input( 'There were words not found in the dictionary. Would you like to abort to fix them? (Y/N)') if user_input.lower() == 'y': return begin = time.time() a.do_align() if args.debug: print('Performed alignment in {} seconds'.format(time.time() - begin)) begin = time.time() a.export_textgrids() if args.debug: print('Exported TextGrids in {} seconds'.format(time.time() - begin)) print('Done! Everything took {} seconds'.format(time.time() - all_begin)) except: conf['dirty'] = True raise finally: with open(conf_path, 'w') as f: yaml.dump(conf, f)
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 = Corpus(args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs, ignore_exceptions=getattr(args, 'ignore_exceptions', False)) 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, args.output_directory, 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() if args.debug: print('Exported TextGrids in {} seconds'.format(time.time() - begin)) print('Done! Everything took {} seconds'.format(time.time() - all_begin)) except: conf['dirty'] = True raise finally: with open(conf_path, 'w') as f: yaml.dump(conf, f)
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) 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 = Corpus(args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs, ignore_exceptions=getattr(args, 'ignore_exceptions', False)) 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, args.output_directory, temp_directory=data_directory, debug=getattr(args, 'debug', False)) if getattr(args, 'errors', False): check = a.test_utterance_transcriptions() if not getattr(args, 'quiet', False) and not check: user_input = input('Would you like to abort to fix transcription issues? (Y/N)') if user_input.lower() == 'y': return 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() if args.debug: print('Exported TextGrids in {} seconds'.format(time.time() - begin)) print('Done! Everything took {} seconds'.format(time.time() - all_begin)) except: conf['dirty'] = True raise finally: with open(conf_path, 'w') as f: yaml.dump(conf, f)
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) 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 = Corpus( args.corpus_directory, data_directory, speaker_characters=args.speaker_characters, num_jobs=args.num_jobs, ignore_exceptions=getattr(args, "ignore_exceptions", False), ) 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, args.output_directory, temp_directory=data_directory, debug=getattr(args, "debug", False), ) if getattr(args, "errors", False): check = a.test_utterance_transcriptions() if not getattr(args, "quiet", False) and not check: user_input = input( "Would you like to abort to fix transcription issues? (Y/N)" ) if user_input.lower() == "y": return 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() if args.debug: print("Exported TextGrids in {} seconds".format(time.time() - begin)) print("Done! Everything took {} seconds".format(time.time() - all_begin)) except: conf["dirty"] = True raise finally: with open(conf_path, "w") as f: yaml.dump(conf, f)