From e6492e3c62f008bf8a3ca74df3cd4457133cb87d Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期日, 05 二月 2023 11:58:48 +0800
Subject: [PATCH] add sampling rate parameter
---
funasr/bin/asr_inference_paraformer.py | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 01237f7..1455517 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -227,6 +227,8 @@
pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], \
predictor_outs[2], predictor_outs[3]
pre_token_length = pre_token_length.round().long()
+ if torch.max(pre_token_length) < 1:
+ return []
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
@@ -394,7 +396,7 @@
# results = speech2text(**batch)
# if len(results) < 1:
# hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
-# results = [[" ", ["<space>"], [2], hyp, 10, 6]] * nbest
+# results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest
# time_end = time.time()
# forward_time = time_end - time_beg
# lfr_factor = results[0][-1]
@@ -527,6 +529,7 @@
nbest: int = 1,
num_workers: int = 1,
output_dir: Optional[str] = None,
+ param_dict: dict = None,
**kwargs,
):
assert check_argument_types()
@@ -576,6 +579,8 @@
data_path_and_name_and_type,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
output_dir_v2: Optional[str] = None,
+ fs: dict = None,
+ param_dict: dict = None,
):
# 3. Build data-iterator
if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -585,6 +590,7 @@
loader = ASRTask.build_streaming_iterator(
data_path_and_name_and_type,
dtype=dtype,
+ fs=fs,
batch_size=batch_size,
key_file=key_file,
num_workers=num_workers,
@@ -621,7 +627,7 @@
results = speech2text(**batch)
if len(results) < 1:
hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
- results = [[" ", ["<space>"], [2], hyp, 10, 6]] * nbest
+ results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest
time_end = time.time()
forward_time = time_end - time_beg
lfr_factor = results[0][-1]
--
Gitblit v1.9.1