From d364a3c40dae16fd123984d0d7be12be8c6c3bab Mon Sep 17 00:00:00 2001
From: huangyuxin <hyxin2014@126.com>
Date: Mon, 30 Aug 2021 09:36:49 +0000
Subject: [PATCH 1/2] fix the bug of sharing cell in BiGRU and BIRNN

---
 deepspeech/models/ds2/rnn.py | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/deepspeech/models/ds2/rnn.py b/deepspeech/models/ds2/rnn.py
index 0d8c9fd2c..3ff91d0af 100644
--- a/deepspeech/models/ds2/rnn.py
+++ b/deepspeech/models/ds2/rnn.py
@@ -29,13 +29,13 @@ __all__ = ['RNNStack']
 
 class RNNCell(nn.RNNCellBase):
     r"""
-    Elman RNN (SimpleRNN) cell. Given the inputs and previous states, it 
+    Elman RNN (SimpleRNN) cell. Given the inputs and previous states, it
     computes the outputs and updates states.
     The formula used is as follows:
     .. math::
         h_{t} & = act(x_{t} + b_{ih} + W_{hh}h_{t-1} + b_{hh})
         y_{t} & = h_{t}
-    
+
     where :math:`act` is for :attr:`activation`.
     """
 
@@ -92,7 +92,7 @@ class RNNCell(nn.RNNCellBase):
 
 class GRUCell(nn.RNNCellBase):
     r"""
-    Gated Recurrent Unit (GRU) RNN cell. Given the inputs and previous states, 
+    Gated Recurrent Unit (GRU) RNN cell. Given the inputs and previous states,
     it computes the outputs and updates states.
     The formula for GRU used is as follows:
     ..  math::
@@ -101,8 +101,8 @@ class GRUCell(nn.RNNCellBase):
         \widetilde{h}_{t} & = \tanh(W_{ic}x_{t} + b_{ic} + r_{t} * (W_{hc}h_{t-1} + b_{hc}))
         h_{t} & = z_{t} * h_{t-1} + (1 - z_{t}) * \widetilde{h}_{t}
         y_{t} & = h_{t}
-    
-    where :math:`\sigma` is the sigmoid fucntion, and * is the elemetwise 
+
+    where :math:`\sigma` is the sigmoid fucntion, and * is the elemetwise
     multiplication operator.
     """
 
@@ -202,7 +202,7 @@ class BiRNNWithBN(nn.Layer):
         self.fw_rnn = nn.RNN(
             self.fw_cell, is_reverse=False, time_major=False)  #[B, T, D]
         self.bw_rnn = nn.RNN(
-            self.fw_cell, is_reverse=True, time_major=False)  #[B, T, D]
+            self.bw_cell, is_reverse=True, time_major=False)  #[B, T, D]
 
     def forward(self, x: paddle.Tensor, x_len: paddle.Tensor):
         # x, shape [B, T, D]
@@ -246,7 +246,7 @@ class BiGRUWithBN(nn.Layer):
         self.fw_rnn = nn.RNN(
             self.fw_cell, is_reverse=False, time_major=False)  #[B, T, D]
         self.bw_rnn = nn.RNN(
-            self.fw_cell, is_reverse=True, time_major=False)  #[B, T, D]
+            self.bw_cell, is_reverse=True, time_major=False)  #[B, T, D]
 
     def forward(self, x, x_len):
         # x, shape [B, T, D]

From 929efe35ca3651d4328789ca9d7548797878f246 Mon Sep 17 00:00:00 2001
From: huangyuxin <hyxin2014@126.com>
Date: Thu, 23 Sep 2021 08:55:48 +0000
Subject: [PATCH 2/2] fix the bug of  parallel using condition

---
 deepspeech/training/trainer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/deepspeech/training/trainer.py b/deepspeech/training/trainer.py
index 79b1562e4..15259f0eb 100644
--- a/deepspeech/training/trainer.py
+++ b/deepspeech/training/trainer.py
@@ -139,7 +139,7 @@ class Trainer():
         """A flag indicating whether the experiment should run with
         multiprocessing.
         """
-        return self.args.nprocs > 0
+        return self.args.nprocs > 1
 
     def init_parallel(self):
         """Init environment for multiprocess training.