From d783b24ba7d8a03dabfa2139fcbf40c216e0ea3d Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 三月 2023 19:34:52 +0800
Subject: [PATCH] Merge pull request #199 from alibaba-damo-academy/dev_xw
---
funasr/bin/asr_inference_paraformer.py | 46 ++++++++++++++++++++++++++++++++++++++--------
1 files changed, 38 insertions(+), 8 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 487f750..e45e575 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -42,6 +42,7 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
+from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
class Speech2Text:
@@ -49,7 +50,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
@@ -190,7 +191,8 @@
@torch.no_grad()
def __call__(
- self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None
+ self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None,
+ begin_time: int = 0, end_time: int = None,
):
"""Inference
@@ -242,6 +244,10 @@
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length, hw_list=self.hotword_list)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
+ if isinstance(self.asr_model, BiCifParaformer):
+ _, _, us_alphas, us_peaks = self.asr_model.calc_predictor_timestamp(enc, enc_len,
+ pre_token_length) # test no bias cif2
+
results = []
b, n, d = decoder_out.size()
for i in range(b):
@@ -284,7 +290,14 @@
else:
text = None
- results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
+ if isinstance(self.asr_model, BiCifParaformer):
+ _, timestamp = ts_prediction_lfr6_standard(us_alphas[i],
+ us_peaks[i],
+ copy.copy(token),
+ vad_offset=begin_time)
+ results.append((text, token, token_int, hyp, timestamp, enc_len_batch_total, lfr_factor))
+ else:
+ results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
# assert check_return_type(results)
return results
@@ -660,11 +673,9 @@
hotword_list_or_file = None
if param_dict is not None:
hotword_list_or_file = param_dict.get('hotword')
-
if 'hotword' in kwargs:
hotword_list_or_file = kwargs['hotword']
-
- if speech2text.hotword_list is None:
+ if hotword_list_or_file is not None or 'hotword' in kwargs:
speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file)
# 3. Build data-iterator
@@ -684,6 +695,11 @@
allow_variable_data_keys=allow_variable_data_keys,
inference=True,
)
+
+ if param_dict is not None:
+ use_timestamp = param_dict.get('use_timestamp', True)
+ else:
+ use_timestamp = True
forward_time_total = 0.0
length_total = 0.0
@@ -726,7 +742,9 @@
result = [results[batch_id][:-2]]
key = keys[batch_id]
- for n, (text, token, token_int, hyp) in zip(range(1, nbest + 1), result):
+ for n, result in zip(range(1, nbest + 1), result):
+ text, token, token_int, hyp = result[0], result[1], result[2], result[3]
+ time_stamp = None if len(result) < 5 else result[4]
# Create a directory: outdir/{n}best_recog
if writer is not None:
ibest_writer = writer[f"{n}best_recog"]
@@ -738,8 +756,20 @@
ibest_writer["rtf"][key] = rtf_cur
if text is not None:
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ if use_timestamp and time_stamp is not None:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
+ else:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token)
+ time_stamp_postprocessed = ""
+ if len(postprocessed_result) == 3:
+ text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], \
+ postprocessed_result[1], \
+ postprocessed_result[2]
+ else:
+ text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
item = {'key': key, 'value': text_postprocessed}
+ if time_stamp_postprocessed != "":
+ item['time_stamp'] = time_stamp_postprocessed
asr_result_list.append(item)
finish_count += 1
# asr_utils.print_progress(finish_count / file_count)
--
Gitblit v1.9.1