From 508e518b12f52eb84843e9cad4b3e51165bb52fb Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 27 二月 2023 16:08:57 +0800
Subject: [PATCH] update cif onnx
---
funasr/export/models/predictor/cif.py | 79 +++++----------------------------------
1 files changed, 11 insertions(+), 68 deletions(-)
diff --git a/funasr/export/models/predictor/cif.py b/funasr/export/models/predictor/cif.py
index 034e233..6f4601d 100644
--- a/funasr/export/models/predictor/cif.py
+++ b/funasr/export/models/predictor/cif.py
@@ -48,11 +48,11 @@
alphas = torch.nn.functional.relu(alphas * self.smooth_factor - self.noise_threshold)
mask = mask.transpose(-1, -2).float()
alphas = alphas * mask
-
alphas = alphas.squeeze(-1)
-
token_num = alphas.sum(-1)
+ mask = mask.squeeze(-1)
+ hidden, alphas, token_num = self.tail_process_fn(hidden, alphas, mask=mask)
acoustic_embeds, cif_peak = cif(hidden, alphas, self.threshold)
return acoustic_embeds, token_num, alphas, cif_peak
@@ -63,18 +63,21 @@
zeros_t = torch.zeros((b, 1), dtype=torch.float32, device=alphas.device)
ones_t = torch.ones_like(zeros_t)
+
mask_1 = torch.cat([mask, zeros_t], dim=1)
mask_2 = torch.cat([ones_t, mask], dim=1)
mask = mask_2 - mask_1
tail_threshold = mask * tail_threshold
- alphas = torch.cat([alphas, tail_threshold], dim=1)
-
+ alphas = torch.cat([alphas, zeros_t], dim=1)
+ alphas = torch.add(alphas, tail_threshold)
+
zeros = torch.zeros((b, 1, d), dtype=hidden.dtype).to(hidden.device)
hidden = torch.cat([hidden, zeros], dim=1)
token_num = alphas.sum(dim=-1)
token_num_floor = torch.floor(token_num)
return hidden, alphas, token_num_floor
+
# @torch.jit.script
# def cif(hidden, alphas, threshold: float):
@@ -113,70 +116,14 @@
# 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().item()
-# # print("type: {}".format(type(max_label_len)))
+# len_labels = torch.floor(alphas.sum(-1)).int()
+# max_label_len = len_labels.max()
# 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)], dtype=l.dtype, device=hidden.device)
+# 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
-
-# @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], 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], 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], dtype=alphas.dtype, device=hidden.device),
-# integrate)
-# cur = torch.where(fire_place,
-# distribution_completion,
-# alpha)
-# remainds = alpha - cur
-#
-# frame += cur[:, None] * hidden[:, t, :]
-# list_frames.append(frame)
-# frame = torch.where(fire_place[:, None].repeat(1, hidden_size),
-# remainds[:, None] * hidden[:, t, :],
-# frame)
-#
-# fires = torch.stack(list_fires, 1)
-# frames = torch.stack(list_frames, 1)
-# len_labels = torch.floor(torch.sum(alphas, dim=1)).int()
-# max_label_len = torch.max(len_labels)
-# pad_num = max_label_len - len_labels
-# pad_num_max = torch.max(pad_num).item()
-# frames_pad_tensor = torch.zeros([int(batch_size), int(pad_num_max), int(hidden_size)], dtype=frames.dtype,
-# device=frames.device)
-# fires_pad_tensor = torch.ones([int(batch_size), int(pad_num_max)], dtype=fires.dtype, device=fires.device)
-# fires_pad_tensor_mask = sequence_mask_scripts(pad_num, maxlen=int(pad_num_max))
-# fires_pad_tensor *= fires_pad_tensor_mask
-# frames_pad = torch.cat([frames, frames_pad_tensor], dim=1)
-# fires_pad = torch.cat([fires, fires_pad_tensor], dim=1)
-# index_bool = fires_pad >= threshold
-# frames_fire = frames_pad[index_bool]
-# frames_fire = torch.reshape(frames_fire, (int(batch_size), -1, int(hidden_size)))
-# frames_fire_mask = sequence_mask_scripts(len_labels, maxlen=int(max_label_len))
-# frames_fire *= frames_fire_mask[:, :, None]
-#
-# return frames_fire, fires
@torch.jit.script
@@ -215,15 +162,11 @@
fires = torch.stack(list_fires, 1)
frames = torch.stack(list_frames, 1)
- # 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, :]
frame_fire = frames[b, fire_idxs[b]]
frame_len = frame_fire.size(0)
frame_fires[b, :frame_len, :] = frame_fire
--
Gitblit v1.9.1