From 55e7a2d880b3322fd89bdb1a27373ffbd842f280 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 22 五月 2024 16:33:17 +0800
Subject: [PATCH] wenetspeech

---
 examples/aishell/paraformer/utils/text2token.py |   17 +++++++++++------
 1 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/examples/aishell/paraformer/utils/text2token.py b/examples/aishell/paraformer/utils/text2token.py
index 56c3913..a89679f 100755
--- a/examples/aishell/paraformer/utils/text2token.py
+++ b/examples/aishell/paraformer/utils/text2token.py
@@ -37,9 +37,7 @@
         help="number of characters to split, i.e., \
                         aabb -> a a b b with -n 1 and aa bb with -n 2",
     )
-    parser.add_argument(
-        "--skip-ncols", "-s", default=0, type=int, help="skip first n columns"
-    )
+    parser.add_argument("--skip-ncols", "-s", default=0, type=int, help="skip first n columns")
     parser.add_argument("--space", default="<space>", type=str, help="space symbol")
     parser.add_argument(
         "--non-lang-syms",
@@ -62,6 +60,12 @@
                         read from SI1279.PHN file -> "sil b r ih sil k s aa r er n aa l
                         sil t er n ih sil t ih v sil" """,
     )
+    parser.add_argument(
+        "--text_format",
+        default="text",
+        type=str,
+        help="text, jsonl",
+    )
     return parser
 
 
@@ -80,12 +84,13 @@
     else:
         f = codecs.getreader("utf-8")(sys.stdin if is_python2 else sys.stdin.buffer)
 
-    sys.stdout = codecs.getwriter("utf-8")(
-        sys.stdout if is_python2 else sys.stdout.buffer
-    )
+    sys.stdout = codecs.getwriter("utf-8")(sys.stdout if is_python2 else sys.stdout.buffer)
     line = f.readline()
     n = args.nchar
     while line:
+        if args.text_format == "jsonl":
+            data = json.loads(line.strip())
+            line = data["target"]
         x = line.split()
         print(" ".join(x[: args.skip_ncols]), end=" ")
         a = " ".join(x[args.skip_ncols :])

--
Gitblit v1.9.1