From d2dc3af1a69ee4075bcfc0c83dc0fb8e3fc1db4e Mon Sep 17 00:00:00 2001
From: yhliang <68215459+yhliang-aslp@users.noreply.github.com>
Date: 星期四, 11 五月 2023 16:31:40 +0800
Subject: [PATCH] Merge pull request #492 from alibaba-damo-academy/dev_smohan
---
funasr/bin/asr_inference_paraformer.py | 52 ++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 40 insertions(+), 12 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index e45e575..5335860 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -41,8 +41,10 @@
from funasr.utils import asr_utils, wav_utils, postprocess_utils
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
+from funasr.models.e2e_asr_contextual_paraformer import NeatContextualParaformer
from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
+from funasr.bin.tp_inference import SpeechText2Timestamp
class Speech2Text:
@@ -235,7 +237,7 @@
pre_token_length = pre_token_length.round().long()
if torch.max(pre_token_length) < 1:
return []
- if not isinstance(self.asr_model, ContextualParaformer):
+ if not isinstance(self.asr_model, ContextualParaformer) and not isinstance(self.asr_model, NeatContextualParaformer):
if self.hotword_list:
logging.warning("Hotword is given but asr model is not a ContextualParaformer.")
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
@@ -540,7 +542,8 @@
ngram_weight: float = 0.9,
nbest: int = 1,
num_workers: int = 1,
-
+ timestamp_infer_config: Union[Path, str] = None,
+ timestamp_model_file: Union[Path, str] = None,
**kwargs,
):
inference_pipeline = inference_modelscope(
@@ -604,11 +607,15 @@
nbest: int = 1,
num_workers: int = 1,
output_dir: Optional[str] = None,
+ timestamp_infer_config: Union[Path, str] = None,
+ timestamp_model_file: Union[Path, str] = None,
param_dict: dict = None,
**kwargs,
):
assert check_argument_types()
-
+ ncpu = kwargs.get("ncpu", 1)
+ torch.set_num_threads(ncpu)
+
if word_lm_train_config is not None:
raise NotImplementedError("Word LM is not implemented")
if ngpu > 1:
@@ -625,7 +632,9 @@
export_mode = param_dict.get("export_mode", False)
else:
hotword_list_or_file = None
-
+
+ if kwargs.get("device", None) == "cpu":
+ ngpu = 0
if ngpu >= 1 and torch.cuda.is_available():
device = "cuda"
else:
@@ -660,6 +669,15 @@
speech2text = Speech2TextExport(**speech2text_kwargs)
else:
speech2text = Speech2Text(**speech2text_kwargs)
+
+ if timestamp_model_file is not None:
+ speechtext2timestamp = SpeechText2Timestamp(
+ timestamp_cmvn_file=cmvn_file,
+ timestamp_model_file=timestamp_model_file,
+ timestamp_infer_config=timestamp_infer_config,
+ )
+ else:
+ speechtext2timestamp = None
def _forward(
data_path_and_name_and_type,
@@ -744,7 +762,17 @@
key = keys[batch_id]
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]
+ timestamp = None if len(result) < 5 else result[4]
+ # conduct timestamp prediction here
+ # timestamp inference requires token length
+ # thus following inference cannot be conducted in batch
+ if timestamp is None and speechtext2timestamp:
+ ts_batch = {}
+ ts_batch['speech'] = batch['speech'][batch_id].unsqueeze(0)
+ ts_batch['speech_lengths'] = torch.tensor([batch['speech_lengths'][batch_id]])
+ ts_batch['text_lengths'] = torch.tensor([len(token)])
+ us_alphas, us_peaks = speechtext2timestamp(**ts_batch)
+ ts_str, timestamp = ts_prediction_lfr6_standard(us_alphas[0], us_peaks[0], token, force_time_shift=-3.0)
# Create a directory: outdir/{n}best_recog
if writer is not None:
ibest_writer = writer[f"{n}best_recog"]
@@ -756,25 +784,25 @@
ibest_writer["rtf"][key] = rtf_cur
if text is not None:
- if use_timestamp and time_stamp is not None:
- postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
+ if use_timestamp and timestamp is not None:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token, timestamp)
else:
postprocessed_result = postprocess_utils.sentence_postprocess(token)
- time_stamp_postprocessed = ""
+ timestamp_postprocessed = ""
if len(postprocessed_result) == 3:
- text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], \
+ text_postprocessed, timestamp_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
+ if timestamp_postprocessed != "":
+ item['timestamp'] = timestamp_postprocessed
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
+ ibest_writer["text"][key] = " ".join(word_lists)
logging.info("decoding, utt: {}, predictions: {}".format(key, text))
rtf_avg = "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))
--
Gitblit v1.9.1