From 79bd015ab0ded4e5aed1b1ecf32fcbc84eefde68 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 03 二月 2023 17:42:47 +0800
Subject: [PATCH] Merge pull request #58 from alibaba-damo-academy/dev
---
funasr/bin/asr_inference_paraformer_vad_punc.py | 365 +++++++--------------------------------------------
1 files changed, 54 insertions(+), 311 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index 265e054..10c1da6 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -1,4 +1,6 @@
#!/usr/bin/env python3
+
+import json
import argparse
import logging
import sys
@@ -37,10 +39,10 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.tasks.vad import VADTask
from funasr.utils.timestamp_tools import time_stamp_lfr6
-from funasr.tasks.punctuation import PunctuationTask
+from funasr.bin.punctuation_infer import Text2Punc
from funasr.torch_utils.forward_adaptor import ForwardAdaptor
from funasr.datasets.preprocessor import CommonPreprocessor
-from funasr.punctuation.text_preprocessor import split_words, split_to_mini_sentence
+from funasr.punctuation.text_preprocessor import split_to_mini_sentence
header_colors = '\033[95m'
end_colors = '\033[0m'
@@ -100,10 +102,13 @@
# logging.info("asr_train_args: {}".format(asr_train_args))
asr_model.to(dtype=getattr(torch, dtype)).eval()
- ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
+ if asr_model.ctc != None:
+ ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
+ scorers.update(
+ ctc=ctc
+ )
token_list = asr_model.token_list
scorers.update(
- ctc=ctc,
length_bonus=LengthBonus(len(token_list)),
)
@@ -171,7 +176,7 @@
self.converter = converter
self.tokenizer = tokenizer
is_use_lm = lm_weight != 0.0 and lm_file is not None
- if ctc_weight == 0.0 and not is_use_lm:
+ if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
beam_search = None
self.beam_search = beam_search
logging.info(f"Beam_search: {self.beam_search}")
@@ -232,6 +237,8 @@
predictor_outs = self.asr_model.calc_predictor(enc, enc_len)
pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], predictor_outs[2], predictor_outs[3]
pre_token_length = pre_token_length.round().long()
+ if torch.max(pre_token_length) < 1:
+ return []
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
@@ -364,201 +371,6 @@
return fbanks, segments
-# def inference(
-# maxlenratio: float,
-# minlenratio: float,
-# batch_size: int,
-# beam_size: int,
-# ngpu: int,
-# ctc_weight: float,
-# lm_weight: float,
-# penalty: float,
-# log_level: Union[int, str],
-# data_path_and_name_and_type,
-# asr_train_config: Optional[str],
-# asr_model_file: Optional[str],
-# cmvn_file: Optional[str] = None,
-# raw_inputs: Union[np.ndarray, torch.Tensor] = None,
-# lm_train_config: Optional[str] = None,
-# lm_file: Optional[str] = None,
-# token_type: Optional[str] = None,
-# key_file: Optional[str] = None,
-# word_lm_train_config: Optional[str] = None,
-# bpemodel: Optional[str] = None,
-# allow_variable_data_keys: bool = False,
-# streaming: bool = False,
-# output_dir: Optional[str] = None,
-# dtype: str = "float32",
-# seed: int = 0,
-# ngram_weight: float = 0.9,
-# nbest: int = 1,
-# num_workers: int = 1,
-# vad_infer_config: Optional[str] = None,
-# vad_model_file: Optional[str] = None,
-# vad_cmvn_file: Optional[str] = None,
-# time_stamp_writer: bool = False,
-# punc_infer_config: Optional[str] = None,
-# punc_model_file: Optional[str] = None,
-# **kwargs,
-# ):
-# assert check_argument_types()
-#
-# if word_lm_train_config is not None:
-# raise NotImplementedError("Word LM is not implemented")
-# if ngpu > 1:
-# raise NotImplementedError("only single GPU decoding is supported")
-#
-# logging.basicConfig(
-# level=log_level,
-# format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
-# )
-#
-# if ngpu >= 1 and torch.cuda.is_available():
-# device = "cuda"
-# else:
-# device = "cpu"
-#
-# # 1. Set random-seed
-# set_all_random_seed(seed)
-#
-# # 2. Build speech2vadsegment
-# speech2vadsegment_kwargs = dict(
-# vad_infer_config=vad_infer_config,
-# vad_model_file=vad_model_file,
-# vad_cmvn_file=vad_cmvn_file,
-# device=device,
-# dtype=dtype,
-# )
-# # logging.info("speech2vadsegment_kwargs: {}".format(speech2vadsegment_kwargs))
-# speech2vadsegment = Speech2VadSegment(**speech2vadsegment_kwargs)
-#
-# # 3. Build speech2text
-# speech2text_kwargs = dict(
-# asr_train_config=asr_train_config,
-# asr_model_file=asr_model_file,
-# cmvn_file=cmvn_file,
-# lm_train_config=lm_train_config,
-# lm_file=lm_file,
-# token_type=token_type,
-# bpemodel=bpemodel,
-# device=device,
-# maxlenratio=maxlenratio,
-# minlenratio=minlenratio,
-# dtype=dtype,
-# beam_size=beam_size,
-# ctc_weight=ctc_weight,
-# lm_weight=lm_weight,
-# ngram_weight=ngram_weight,
-# penalty=penalty,
-# nbest=nbest,
-# frontend_conf=frontend_conf,
-# )
-# speech2text = Speech2Text(**speech2text_kwargs)
-#
-# text2punc = Text2Punc(punc_infer_config, punc_model_file, device=device, dtype=dtype)
-#
-# # 3. Build data-iterator
-# loader = ASRTask.build_streaming_iterator(
-# data_path_and_name_and_type,
-# dtype=dtype,
-# batch_size=1,
-# key_file=key_file,
-# num_workers=num_workers,
-# preprocess_fn=VADTask.build_preprocess_fn(speech2vadsegment.vad_infer_args, False),
-# collate_fn=VADTask.build_collate_fn(speech2vadsegment.vad_infer_args, False),
-# allow_variable_data_keys=allow_variable_data_keys,
-# inference=True,
-# )
-#
-# forward_time_total = 0.0
-# length_total = 0.0
-# finish_count = 0
-# file_count = 1
-# # 7 .Start for-loop
-# asr_result_list = []
-# if output_dir is not None:
-# writer = DatadirWriter(output_dir)
-# else:
-# writer = None
-#
-# for keys, batch in loader:
-# assert isinstance(batch, dict), type(batch)
-# assert all(isinstance(s, str) for s in keys), keys
-# _bs = len(next(iter(batch.values())))
-# assert len(keys) == _bs, f"{len(keys)} != {_bs}"
-# # batch = {k: v for k, v in batch.items() if not k.endswith("_lengths")}
-#
-# logging.info("decoding, utt_id: {}".format(keys))
-# # N-best list of (text, token, token_int, hyp_object)
-# time_beg = time.time()
-# vad_results = speech2vadsegment(**batch)
-# time_end = time.time()
-# fbanks, vadsegments = vad_results[0], vad_results[1]
-# for i, segments in enumerate(vadsegments):
-# result_segments = [["", [], [], ]]
-# for j, segment_idx in enumerate(segments):
-# bed_idx, end_idx = int(segment_idx[0]/10), int(segment_idx[1]/10)
-# segment = fbanks[:, bed_idx:end_idx, :].to(device)
-# speech_lengths = torch.Tensor([end_idx-bed_idx]).int().to(device)
-# batch = {"speech": segment, "speech_lengths": speech_lengths, "begin_time": vadsegments[i][j][0], "end_time": vadsegments[i][j][1]}
-# results = speech2text(**batch)
-# if len(results) < 1:
-# hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
-# results = [[" ", ["<space>"], [2], 10, 6]] * nbest
-# time_end = time.time()
-# forward_time = time_end - time_beg
-# lfr_factor = results[0][-1]
-# length = results[0][-2]
-# forward_time_total += forward_time
-# length_total += length
-# logging.info(
-# "decoding, feature length: {}, forward_time: {:.4f}, rtf: {:.4f}".
-# format(length, forward_time, 100 * forward_time / (length*lfr_factor)))
-# result_cur = [results[0][:-2]]
-# if j == 0:
-# result_segments = result_cur
-# else:
-# result_segments = [[result_segments[0][i] + result_cur[0][i] for i in range(len(result_cur[0]))]]
-#
-# key = keys[0]
-# result = result_segments[0]
-# text, token, token_int, time_stamp = result
-#
-# # Create a directory: outdir/{n}best_recog
-# if writer is not None:
-# ibest_writer = writer[f"1best_recog"]
-#
-# # Write the result to each file
-# ibest_writer["token"][key] = " ".join(token)
-# ibest_writer["token_int"][key] = " ".join(map(str, token_int))
-#
-# if text is not None:
-# postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
-# if len(postprocessed_result) == 3:
-# text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1], postprocessed_result[2]
-# text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
-# text_postprocessed_punc_time_stamp = "predictions: {} time_stamp: {}".format(text_postprocessed_punc, time_stamp_postprocessed)
-# else:
-# text_postprocessed = postprocessed_result
-# time_stamp_postprocessed = None
-# word_lists = None
-# text_postprocessed_punc_time_stamp = None
-# punc_id_list = None
-#
-# item = {'key': key, 'value': text_postprocessed_punc_time_stamp, 'text': text_postprocessed, 'time_stamp': time_stamp_postprocessed, 'punc': punc_id_list}
-# asr_result_list.append(item)
-# finish_count += 1
-# # asr_utils.print_progress(finish_count / file_count)
-# if writer is not None:
-# ibest_writer["text"][key] = text_postprocessed
-# if time_stamp_writer and time_stamp_postprocessed is not None:
-# ibest_writer["time_stamp"][key] = " ".join(["-".join(map(str, ts)) for ts in time_stamp_postprocessed])
-#
-# logging.info("decoding, utt: {}, predictions: {}, time_stamp: {}".format(key, text_postprocessed_punc, time_stamp_postprocessed))
-#
-# logging.info("decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".
-# format(length_total, forward_time_total, 100 * forward_time_total / (length_total*lfr_factor)))
-# return asr_result_list
def inference(
maxlenratio: float,
@@ -666,9 +478,11 @@
vad_infer_config: Optional[str] = None,
vad_model_file: Optional[str] = None,
vad_cmvn_file: Optional[str] = None,
- time_stamp_writer: bool = False,
+ time_stamp_writer: bool = True,
punc_infer_config: Optional[str] = None,
punc_model_file: Optional[str] = None,
+ outputs_dict: Optional[bool] = True,
+ param_dict: dict = None,
**kwargs,
):
assert check_argument_types()
@@ -725,10 +539,16 @@
speech2text = Speech2Text(**speech2text_kwargs)
text2punc = Text2Punc(punc_infer_config, punc_model_file, device=device, dtype=dtype)
+
+ if output_dir is not None:
+ writer = DatadirWriter(output_dir)
+ ibest_writer = writer[f"1best_recog"]
+ ibest_writer["token_list"][""] = " ".join(speech2text.asr_train_args.token_list)
def _forward(data_path_and_name_and_type,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
output_dir_v2: Optional[str] = None,
+ param_dict: dict = None,
):
# 3. Build data-iterator
if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -751,11 +571,15 @@
length_total = 0.0
finish_count = 0
file_count = 1
+ lfr_factor = 6
# 7 .Start for-loop
asr_result_list = []
output_path = output_dir_v2 if output_dir_v2 is not None else output_dir
if output_path is not None:
writer = DatadirWriter(output_path)
+ ibest_writer = writer[f"1best_recog"]
+ # ibest_writer["punc_dict"][""] = " ".join(punc_infer_config.punc_list)
+ # ibest_writer["token_list"][""] = " ".join(asr_train_config.token_list)
else:
writer = None
@@ -783,7 +607,7 @@
results = speech2text(**batch)
if len(results) < 1:
hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
- results = [[" ", ["<space>"], [2], 10, 6]] * nbest
+ results = [[" ", ["sil"], [2], 0, 1, 6]] * nbest
time_end = time.time()
forward_time = time_end - time_beg
lfr_factor = results[0][-1]
@@ -801,15 +625,15 @@
key = keys[0]
result = result_segments[0]
- text, token, token_int, time_stamp = result
+ text, token, token_int = result[0], result[1], result[2]
+ time_stamp = None if len(result) < 4 else result[3]
# Create a directory: outdir/{n}best_recog
if writer is not None:
- ibest_writer = writer[f"1best_recog"]
-
# Write the result to each file
ibest_writer["token"][key] = " ".join(token)
- # ibest_writer["token_int"][key] = " ".join(map(str, token_int))
+ ibest_writer["token_int"][key] = " ".join(map(str, token_int))
+ ibest_writer["vad"][key] = "{}".format(vadsegments)
if text is not None:
postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
@@ -817,123 +641,42 @@
text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], \
postprocessed_result[1], \
postprocessed_result[2]
- text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
- text_postprocessed_punc_time_stamp = "predictions: {} time_stamp: {}".format(
- text_postprocessed_punc, time_stamp_postprocessed)
+ if len(word_lists) > 0:
+ text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
+ text_postprocessed_punc_time_stamp = json.dumps({"predictions": text_postprocessed_punc,
+ "time_stamp": time_stamp_postprocessed},
+ ensure_ascii=False)
+ else:
+ text_postprocessed_punc = ""
+ punc_id_list = []
+ text_postprocessed_punc_time_stamp = ""
+
else:
- text_postprocessed = postprocessed_result
- time_stamp_postprocessed = None
- word_lists = None
- text_postprocessed_punc_time_stamp = None
- punc_id_list = None
-
- item = {'key': key, 'value': text_postprocessed_punc_time_stamp, 'text': text_postprocessed,
- 'time_stamp': time_stamp_postprocessed, 'punc': punc_id_list}
+ text_postprocessed = ""
+ time_stamp_postprocessed = ""
+ word_lists = ""
+ text_postprocessed_punc_time_stamp = ""
+ punc_id_list = ""
+ text_postprocessed_punc = ""
+
+ item = {'key': key, 'value': text_postprocessed_punc, 'text_postprocessed': text_postprocessed,
+ 'time_stamp': time_stamp_postprocessed, 'token': token}
asr_result_list.append(item)
finish_count += 1
# asr_utils.print_progress(finish_count / file_count)
if writer is not None:
ibest_writer["text"][key] = text_postprocessed
- if time_stamp_writer and time_stamp_postprocessed is not None:
- ibest_writer["time_stamp"][key] = " ".join(
- ["-".join(map(str, ts)) for ts in time_stamp_postprocessed])
+ ibest_writer["punc_id"][key] = "{}".format(punc_id_list)
+ ibest_writer["text_with_punc"][key] = text_postprocessed_punc_time_stamp
+ if time_stamp_postprocessed is not None:
+ ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
logging.info("decoding, utt: {}, predictions: {}, time_stamp: {}".format(key, text_postprocessed_punc,
time_stamp_postprocessed))
logging.info("decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".
- format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor)))
+ format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor+1e-6)))
return asr_result_list
- return _forward
-
-def Text2Punc(
- train_config: Optional[str],
- model_file: Optional[str],
- device: str = "cpu",
- dtype: str = "float32",
-):
-
- # 2. Build Model
- model, train_args = PunctuationTask.build_model_from_file(
- train_config, model_file, device)
- # Wrape model to make model.nll() data-parallel
- wrapped_model = ForwardAdaptor(model, "inference")
- wrapped_model.to(dtype=getattr(torch, dtype)).to(device=device).eval()
- # logging.info(f"Model:\n{model}")
- punc_list = train_args.punc_list
- period = 0
- for i in range(len(punc_list)):
- if punc_list[i] == ",":
- punc_list[i] = "锛�"
- elif punc_list[i] == "?":
- punc_list[i] = "锛�"
- elif punc_list[i] == "銆�":
- period = i
-
- preprocessor = CommonPreprocessor(
- train=False,
- token_type="word",
- token_list=train_args.token_list,
- bpemodel=train_args.bpemodel,
- text_cleaner=train_args.cleaner,
- g2p_type=train_args.g2p,
- text_name="text",
- non_linguistic_symbols=train_args.non_linguistic_symbols,
- )
-
- print("start decoding!!!")
-
- def _forward(words, split_size = 20):
- cache_sent = []
- mini_sentences = split_to_mini_sentence(words, split_size)
- new_mini_sentence = ""
- new_mini_sentence_punc = ""
- for mini_sentence_i in range(len(mini_sentences)):
- mini_sentence = mini_sentences[mini_sentence_i]
- mini_sentence = cache_sent + mini_sentence
- data = {"text": " ".join(mini_sentence)}
- batch = preprocessor(data=data, uid="12938712838719")
- batch["text_lengths"] = torch.from_numpy(np.array([len(batch["text"])], dtype='int32'))
- batch["text"] = torch.from_numpy(batch["text"])
- # Extend one dimension to fake a batch dim.
- batch["text"] = torch.unsqueeze(batch["text"], 0)
- batch = to_device(batch, device)
- y, _ = wrapped_model(**batch)
- _, indices = y.view(-1, y.shape[-1]).topk(1, dim=1)
- punctuations = indices
- if indices.size()[0] != 1:
- punctuations = torch.squeeze(indices)
- assert punctuations.size()[0] == len(mini_sentence)
-
- # Search for the last Period/QuestionMark as cache
- if mini_sentence_i < len(mini_sentences) - 1:
- sentenceEnd = -1
- for i in range(len(punctuations) - 2, 1, -1):
- if punc_list[punctuations[i]] == "銆�" or punc_list[punctuations[i]] == "锛�":
- sentenceEnd = i
- break
-
- cache_sent = mini_sentence[sentenceEnd + 1:]
- mini_sentence = mini_sentence[0:sentenceEnd + 1]
- punctuations = punctuations[0:sentenceEnd + 1]
-
- # if len(punctuations) == 0:
- # continue
-
- punctuations_np = punctuations.cpu().numpy()
- new_mini_sentence_punc += "".join([str(x) for x in punctuations_np])
- words_with_punc = []
- for i in range(len(mini_sentence)):
- if i > 0:
- if len(mini_sentence[i][0].encode()) == 1 and len(mini_sentence[i - 1][0].encode()) == 1:
- mini_sentence[i] = " " + mini_sentence[i]
- words_with_punc.append(mini_sentence[i])
- if punc_list[punctuations[i]] != "_":
- words_with_punc.append(punc_list[punctuations[i]])
- new_mini_sentence += "".join(words_with_punc)
-
- return new_mini_sentence, new_mini_sentence_punc
-
return _forward
def get_parser():
--
Gitblit v1.9.1