From a0ffe57b05679d91e56227ce1109a5d725d93192 Mon Sep 17 00:00:00 2001
From: 语帆 <yf352572@alibaba-inc.com>
Date: 星期三, 21 二月 2024 16:48:33 +0800
Subject: [PATCH] test
---
funasr/auto/auto_model.py | 11 +++++++++--
funasr/models/contextual_paraformer/model.py | 24 +++++++++++++++++++-----
2 files changed, 28 insertions(+), 7 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index e95cfd8..4cc52a5 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -24,7 +24,7 @@
from funasr.models.campplus.cluster_backend import ClusterBackend
except:
print("If you want to use the speaker diarization, please `pip install hdbscan`")
-
+import pdb
def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
"""
@@ -210,13 +210,15 @@
kwargs.update(cfg)
model = self.model if model is None else model
model.eval()
+ pdb.set_trace()
batch_size = kwargs.get("batch_size", 1)
# if kwargs.get("device", "cpu") == "cpu":
# batch_size = 1
key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None), key=key)
-
+ pdb.set_trace()
+
speed_stats = {}
asr_result_list = []
num_samples = len(data_list)
@@ -224,20 +226,25 @@
pbar = tqdm(colour="blue", total=num_samples, dynamic_ncols=True) if not disable_pbar else None
time_speech_total = 0.0
time_escape_total = 0.0
+ pdb.set_trace()
for beg_idx in range(0, num_samples, batch_size):
+ pdb.set_trace()
end_idx = min(num_samples, beg_idx + batch_size)
data_batch = data_list[beg_idx:end_idx]
key_batch = key_list[beg_idx:end_idx]
batch = {"data_in": data_batch, "key": key_batch}
+ pdb.set_trace()
if (end_idx - beg_idx) == 1 and kwargs.get("data_type", None) == "fbank": # fbank
batch["data_in"] = data_batch[0]
batch["data_lengths"] = input_len
time1 = time.perf_counter()
with torch.no_grad():
+ pdb.set_trace()
results, meta_data = model.inference(**batch, **kwargs)
time2 = time.perf_counter()
+ pdb.set_trace()
asr_result_list.extend(results)
# batch_data_time = time_per_frame_s * data_batch_i["speech_lengths"].sum().item()
diff --git a/funasr/models/contextual_paraformer/model.py b/funasr/models/contextual_paraformer/model.py
index 598c074..655ca6f 100644
--- a/funasr/models/contextual_paraformer/model.py
+++ b/funasr/models/contextual_paraformer/model.py
@@ -63,7 +63,6 @@
crit_attn_smooth = kwargs.get("crit_attn_smooth", 0.0)
bias_encoder_dropout_rate = kwargs.get("bias_encoder_dropout_rate", 0.0)
- pdb.set_trace()
if bias_encoder_type == 'lstm':
self.bias_encoder = torch.nn.LSTM(inner_dim, inner_dim, 1, batch_first=True, dropout=bias_encoder_dropout_rate)
self.bias_embed = torch.nn.Embedding(self.vocab_size, inner_dim)
@@ -81,7 +80,6 @@
if self.crit_attn_weight > 0:
self.attn_loss = torch.nn.L1Loss()
self.crit_attn_smooth = crit_attn_smooth
- pdb.set_trace()
def forward(
@@ -313,20 +311,24 @@
**kwargs,
):
# init beamsearch
+ pdb.set_trace()
is_use_ctc = kwargs.get("decoding_ctc_weight", 0.0) > 0.00001 and self.ctc != None
is_use_lm = kwargs.get("lm_weight", 0.0) > 0.00001 and kwargs.get("lm_file", None) is not None
if self.beam_search is None and (is_use_lm or is_use_ctc):
logging.info("enable beam_search")
self.init_beam_search(**kwargs)
self.nbest = kwargs.get("nbest", 1)
-
+ pdb.set_trace()
meta_data = {}
# extract fbank feats
time1 = time.perf_counter()
+ pdb.set_trace()
audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
+ pdb.set_trace()
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
+ pdb.set_trace()
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
frontend=frontend)
time3 = time.perf_counter()
@@ -334,38 +336,50 @@
meta_data[
"batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
+ pdb.set_trace()
speech = speech.to(device=kwargs["device"])
speech_lengths = speech_lengths.to(device=kwargs["device"])
# hotword
+ pdb.set_trace()
self.hotword_list = self.generate_hotwords_list(kwargs.get("hotword", None), tokenizer=tokenizer, frontend=frontend)
+ pdb.set_trace()
+
# Encoder
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
if isinstance(encoder_out, tuple):
encoder_out = encoder_out[0]
-
+ pdb.set_trace()
+
+
# predictor
predictor_outs = self.calc_predictor(encoder_out, encoder_out_lens)
pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], \
predictor_outs[2], predictor_outs[3]
+ pdb.set_trace()
pre_token_length = pre_token_length.round().long()
if torch.max(pre_token_length) < 1:
return []
-
+ pdb.set_trace()
+
decoder_outs = self.cal_decoder_with_predictor(encoder_out, encoder_out_lens,
pre_acoustic_embeds,
pre_token_length,
hw_list=self.hotword_list,
clas_scale=kwargs.get("clas_scale", 1.0))
+ pdb.set_trace()
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
+ pdb.set_trace()
results = []
b, n, d = decoder_out.size()
+ pdb.set_trace()
for i in range(b):
x = encoder_out[i, :encoder_out_lens[i], :]
am_scores = decoder_out[i, :pre_token_length[i], :]
+ pdb.set_trace()
if self.beam_search is not None:
nbest_hyps = self.beam_search(
x=x, am_scores=am_scores, maxlenratio=kwargs.get("maxlenratio", 0.0),
--
Gitblit v1.9.1