From 31eed1834f9ff17d6246008f64d3e061f58ef80a Mon Sep 17 00:00:00 2001
From: 凌匀 <ailsa.zly@alibaba-inc.com>
Date: 星期一, 27 二月 2023 13:33:55 +0800
Subject: [PATCH] in_cache & support soundfile read
---
funasr/export/models/predictor/cif.py | 86 ++++++++++++------------------------------
1 files changed, 25 insertions(+), 61 deletions(-)
diff --git a/funasr/export/models/predictor/cif.py b/funasr/export/models/predictor/cif.py
index 32a3c13..c8df7f3 100644
--- a/funasr/export/models/predictor/cif.py
+++ b/funasr/export/models/predictor/cif.py
@@ -16,6 +16,11 @@
return mask.type(dtype).to(device) if device is not None else mask.type(dtype)
+def sequence_mask_scripts(lengths, maxlen:int):
+ row_vector = torch.arange(0, maxlen, 1).type(lengths.dtype).to(lengths.device)
+ matrix = torch.unsqueeze(lengths, dim=-1)
+ mask = row_vector < matrix
+ return mask.type(torch.float32).to(lengths.device)
class CifPredictorV2(nn.Module):
def __init__(self, model):
@@ -71,28 +76,29 @@
return hidden, alphas, token_num_floor
+
@torch.jit.script
def cif(hidden, alphas, threshold: float):
batch_size, len_time, hidden_size = hidden.size()
threshold = torch.tensor([threshold], dtype=alphas.dtype).to(alphas.device)
# loop varss
- integrate = torch.zeros([batch_size], device=hidden.device)
- frame = torch.zeros([batch_size, hidden_size], device=hidden.device)
+ integrate = torch.zeros([batch_size], dtype=alphas.dtype, device=hidden.device)
+ frame = torch.zeros([batch_size, hidden_size], dtype=hidden.dtype, device=hidden.device)
# intermediate vars along time
list_fires = []
list_frames = []
for t in range(len_time):
alpha = alphas[:, t]
- distribution_completion = torch.ones([batch_size], device=hidden.device) - integrate
+ distribution_completion = torch.ones([batch_size], dtype=alphas.dtype, device=hidden.device) - integrate
integrate += alpha
list_fires.append(integrate)
fire_place = integrate >= threshold
integrate = torch.where(fire_place,
- integrate - torch.ones([batch_size], device=hidden.device),
+ integrate - torch.ones([batch_size], dtype=alphas.dtype, device=hidden.device),
integrate)
cur = torch.where(fire_place,
distribution_completion,
@@ -107,62 +113,20 @@
fires = torch.stack(list_fires, 1)
frames = torch.stack(list_frames, 1)
- list_ls = []
- len_labels = torch.round(alphas.sum(-1)).int()
- max_label_len = len_labels.max()
+ # list_ls = []
+ len_labels = torch.round(alphas.sum(-1)).type(torch.int32)
+ # max_label_len = int(torch.max(len_labels).item())
+ # print("type: {}".format(type(max_label_len)))
+ fire_idxs = fires >= threshold
+ frame_fires = torch.zeros_like(hidden)
+ max_label_len = frames[0, fire_idxs[0]].size(0)
for b in range(batch_size):
- fire = fires[b, :]
- l = torch.index_select(frames[b, :, :], 0, torch.nonzero(fire >= threshold).squeeze())
- pad_l = torch.zeros([int(max_label_len - l.size(0)), int(hidden_size)], device=hidden.device)
- list_ls.append(torch.cat([l, pad_l], 0))
- return torch.stack(list_ls, 0), fires
-
-
-def CifPredictorV2_test():
- x = torch.rand([2, 21, 2])
- x_len = torch.IntTensor([6, 21])
+ # fire = fires[b, :]
+ frame_fire = frames[b, fire_idxs[b]]
+ frame_len = frame_fire.size(0)
+ frame_fires[b, :frame_len, :] = frame_fire
- mask = sequence_mask(x_len, maxlen=x.size(1), dtype=x.dtype)
- x = x * mask[:, :, None]
-
- predictor_scripts = torch.jit.script(CifPredictorV2(2, 1, 1))
- # cif_output, cif_length, alphas, cif_peak = predictor_scripts(x, mask=mask[:, None, :])
- predictor_scripts.save('test.pt')
- loaded = torch.jit.load('test.pt')
- cif_output, cif_length, alphas, cif_peak = loaded(x, mask=mask[:, None, :])
- # print(cif_output)
- print(predictor_scripts.code)
- # predictor = CifPredictorV2(2, 1, 1)
- # cif_output, cif_length, alphas, cif_peak = predictor(x, mask=mask[:, None, :])
- print(cif_output)
-
-
-def CifPredictorV2_export_test():
- x = torch.rand([2, 21, 2])
- x_len = torch.IntTensor([6, 21])
-
- mask = sequence_mask(x_len, maxlen=x.size(1), dtype=x.dtype)
- x = x * mask[:, :, None]
-
- # predictor_scripts = torch.jit.script(CifPredictorV2(2, 1, 1))
- # cif_output, cif_length, alphas, cif_peak = predictor_scripts(x, mask=mask[:, None, :])
- predictor = CifPredictorV2(2, 1, 1)
- predictor_trace = torch.jit.trace(predictor, (x, mask[:, None, :]))
- predictor_trace.save('test_trace.pt')
- loaded = torch.jit.load('test_trace.pt')
-
- x = torch.rand([3, 30, 2])
- x_len = torch.IntTensor([6, 20, 30])
- mask = sequence_mask(x_len, maxlen=x.size(1), dtype=x.dtype)
- x = x * mask[:, :, None]
- cif_output, cif_length, alphas, cif_peak = loaded(x, mask=mask[:, None, :])
- print(cif_output)
- # print(predictor_trace.code)
- # predictor = CifPredictorV2(2, 1, 1)
- # cif_output, cif_length, alphas, cif_peak = predictor(x, mask=mask[:, None, :])
- # print(cif_output)
-
-
-if __name__ == '__main__':
- # CifPredictorV2_test()
- CifPredictorV2_export_test()
\ No newline at end of file
+ if frame_len >= max_label_len:
+ max_label_len = frame_len
+ frame_fires = frame_fires[:, :max_label_len, :]
+ return frame_fires, fires
--
Gitblit v1.9.1