From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky

---
 funasr/bin/asr_inference_paraformer.py |   52 +++++++++++++++++++++++++++++++++++++++-------------
 1 files changed, 39 insertions(+), 13 deletions(-)

diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 8265fc5..8cbd419 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -42,7 +42,8 @@
 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 time_stamp_lfr6_pl, time_stamp_sentence
+from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
+from funasr.bin.tp_inference import SpeechText2Timestamp
 
 
 class Speech2Text:
@@ -50,7 +51,7 @@
 
     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), ...]
@@ -245,7 +246,7 @@
             decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
 
         if isinstance(self.asr_model, BiCifParaformer):
-            _, _, us_alphas, us_cif_peak = self.asr_model.calc_predictor_timestamp(enc, enc_len,
+            _, _, us_alphas, us_peaks = self.asr_model.calc_predictor_timestamp(enc, enc_len,
                                                                                    pre_token_length)  # test no bias cif2
 
         results = []
@@ -291,7 +292,10 @@
                     text = None
 
                 if isinstance(self.asr_model, BiCifParaformer):
-                    timestamp = time_stamp_lfr6_pl(us_alphas[i], us_cif_peak[i], copy.copy(token), begin_time, end_time)
+                    _, 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))
@@ -537,7 +541,8 @@
         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(
@@ -601,6 +606,8 @@
         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,
 ):
@@ -657,6 +664,15 @@
         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,
@@ -741,7 +757,17 @@
                 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"]
@@ -753,25 +779,25 @@
                         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