def __init__(self, lm_weight=2.0, lexicon_path="WER_data/lexicon.txt", token_path="WER_data/letters.lst", lm_path="WER_data/4-gram.bin"): lexicon = load_words(lexicon_path) word_dict = create_word_dict(lexicon) self.token_dict = Dictionary(token_path) self.lm = KenLM(lm_path, word_dict) self.sil_idx = self.token_dict.get_index("|") self.unk_idx = word_dict.get_index("<unk>") self.token_dict.add_entry("#") self.blank_idx = self.token_dict.get_index('#') self.trie = Trie(self.token_dict.index_size(), self.sil_idx) start_state = self.lm.start(start_with_nothing=False) for word, spellings in lexicon.items(): usr_idx = word_dict.get_index(word) _, score = self.lm.score(start_state, usr_idx) for spelling in spellings: # max_reps should be 1; using 0 here to match DecoderTest bug spelling_idxs = tkn_to_idx(spelling, self.token_dict, max_reps=0) self.trie.insert(spelling_idxs, usr_idx, score) self.trie.smear(SmearingMode.MAX) self.opts = DecoderOptions(beam_size=2500, beam_threshold=100.0, lm_weight=lm_weight, word_score=2.0, unk_score=-math.inf, log_add=False, sil_weight=-1, criterion_type=CriterionType.CTC)
return np.frombuffer(file.read(N * N * 4), dtype=np.float32) def assert_near(x, y, tol): assert abs(x - y) <= tol # load test files T, N = load_TN(os.path.join(testing_data_path, "TN.bin")) emissions = load_emissions(os.path.join(testing_data_path, "emission.bin")) transitions = load_transitions( os.path.join(testing_data_path, "transition.bin")) lexicon = loadWords(os.path.join(testing_data_path, "words.lst")) wordDict = createWordDict(lexicon) tokenDict = Dictionary(os.path.join(testing_data_path, "letters.lst")) tokenDict.addEntry("1") lm = KenLM(os.path.join(testing_data_path, "lm.arpa"), wordDict) # test LM #sentence = ["the", "cat", "sat", "on", "the", "mat"] #lm_state = lm.start(False) #total_score = 0 #lm_score_target = [-1.05971, -4.19448, -3.33383, -2.76726, -1.16237, -4.64589] #for i in range(len(sentence)): # lm_state, lm_score = lm.score(lm_state, wordDict.getIndex(sentence[i])) # assert_near(lm_score, lm_score_target[i], 1e-5) # total_score += lm_score #lm_state, lm_score = lm.finish(lm_state) #total_score += lm_score
# load test files # load time and number of tokens for dumped acoustic scores T, N = load_tn(os.path.join(data_path, "TN.bin")) # load emissions [Batch=1, Time, Ntokens] emissions = load_emissions(os.path.join(data_path, "emission.bin")) # load transitions (from ASG loss optimization) [Ntokens, Ntokens] transitions = load_transitions(os.path.join(data_path, "transition.bin")) # load lexicon file, which defines spelling of words # the format word and its tokens spelling separated by the spaces, # for example for letters tokens with ASG loss: # ann a n 1 | lexicon = load_words(os.path.join(data_path, "words.lst")) # read lexicon and store it in the w2l dictionary word_dict = create_word_dict(lexicon) # create w2l dict with tokens set (letters in this example) token_dict = Dictionary(os.path.join(data_path, "letters.lst")) # add repetition symbol as soon as we have ASG acoustic model token_dict.add_entry("1") # create Kenlm language model lm = KenLM(os.path.join(data_path, "lm.arpa"), word_dict) # test LM sentence = ["the", "cat", "sat", "on", "the", "mat"] # start LM with nothing, get its current state lm_state = lm.start(False) total_score = 0 lm_score_target = [ -1.05971, -4.19448, -3.33383, -2.76726, -1.16237, -4.64589 ] # iterate over words in the sentence for i in range(len(sentence)):