From b15db52e4e67da8a133a67e8ffa415386de48b40 Mon Sep 17 00:00:00 2001
From: zhuyunfeng <10596244@qq.com>
Date: 星期二, 09 五月 2023 23:03:15 +0800
Subject: [PATCH] Add contributor
---
funasr/bin/asr_inference_paraformer.py | 84 +++++++++++++++++++++++++++++++++++------
1 files changed, 71 insertions(+), 13 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 487f750..5335860 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -41,7 +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:
@@ -49,7 +52,7 @@
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 +193,8 @@
@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
@@ -233,7 +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)
@@ -241,6 +245,10 @@
else:
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()
@@ -284,7 +292,14 @@
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
@@ -527,7 +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(
@@ -591,11 +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:
@@ -612,7 +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:
@@ -648,6 +670,15 @@
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,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
@@ -660,11 +691,9 @@
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 +713,11 @@
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 +760,19 @@
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]
+ 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"]
@@ -738,13 +784,25 @@
ibest_writer["rtf"][key] = rtf_cur
if text is not None:
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ if use_timestamp and timestamp is not None:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token, timestamp)
+ else:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token)
+ timestamp_postprocessed = ""
+ if len(postprocessed_result) == 3:
+ 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 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