From 3258d2be0ad4944f0c7a359164cc25f2a32504c9 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 21 三月 2023 14:01:29 +0800
Subject: [PATCH] debugging

---
 funasr/bin/asr_inference_paraformer.py |   29 +++++++++++++++++++++++++----
 1 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 588b1bc..7e159fd 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -43,6 +43,7 @@
 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
+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 = []
@@ -292,7 +293,7 @@
 
                 if isinstance(self.asr_model, BiCifParaformer):
                     _, timestamp = ts_prediction_lfr6_standard(us_alphas[i], 
-                                                            us_cif_peak[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))
@@ -540,7 +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(
@@ -604,6 +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,
 ):
@@ -660,6 +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,
@@ -743,8 +756,16 @@
 
                 key = keys[batch_id]
                 for n, result in zip(range(1, nbest + 1), result):
+                    # import pdb; pdb.set_trace()
                     text, token, token_int, hyp = result[0], result[1], result[2], result[3]
                     time_stamp = None if len(result) < 5 else result[4]
+                    # conduct timestamp prediction here
+                    if time_stamp is None and speechtext2timestamp:
+                        ts_batch = {}
+                        ts_batch['speech'] = batch['speech'][batch_id].squeeze(0)
+                        ts_batch['speech_lengths'] = torch.tensor([batch['speech_lengths'][batch_id]])
+                        ts_batch['text_lengths'] = torch.tensor([len(token)])
+                        import pdb; pdb.set_trace()
                     # Create a directory: outdir/{n}best_recog
                     if writer is not None:
                         ibest_writer = writer[f"{n}best_recog"]

--
Gitblit v1.9.1