From c553a8db1712c2a5deeef5bbb68bd1fdf8d61ab7 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 13 六月 2024 17:38:01 +0800
Subject: [PATCH] decoding
---
funasr/datasets/openai_datasets/index_ds.py | 24 +++++++++++++++---------
1 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/funasr/datasets/openai_datasets/index_ds.py b/funasr/datasets/openai_datasets/index_ds.py
index 1c48cd2..9943e2a 100644
--- a/funasr/datasets/openai_datasets/index_ds.py
+++ b/funasr/datasets/openai_datasets/index_ds.py
@@ -15,11 +15,6 @@
def __init__(self, path: str, **kwargs):
super().__init__()
- self.max_source_length = kwargs.get("max_source_length", 2048)
- self.min_source_length = kwargs.get("min_source_length", 0)
- self.max_target_length = kwargs.get("max_target_length", 2048)
- self.min_target_length = kwargs.get("min_target_length", 0)
- self.max_token_length = kwargs.get("max_token_length", 2200)
is_training = kwargs.get("is_training", True)
if not (path.endswith(".jsonl") or path.endswith(".json")):
@@ -48,7 +43,10 @@
for file_json in file_list:
with open(file_json.strip(), encoding="utf-8") as fin:
for line in fin:
- data = json.loads(line.strip())["messages"]
+ data_dict = json.loads(line.strip())
+ data = data_dict["messages"]
+ speech_length = data_dict.get("speech_length", -1) // 8
+ text_length = data_dict.get("text_length", 0)
system, user, assistant = [], [], []
for i, item in enumerate(data):
@@ -63,7 +61,12 @@
system = system * len(user)
- contents_i = {"system": system, "user": user, "assistant": assistant}
+ contents_i = {
+ "system": system,
+ "user": user,
+ "assistant": assistant,
+ "source_len": speech_length + text_length,
+ }
contents.append(contents_i)
self.contents = contents
@@ -80,11 +83,14 @@
return data
def get_source_len(self, data_dict):
- return len(data_dict["system"]) + len(data_dict["user"])
+ source_len = data_dict.get("source_len", -1)
+ if source_len < 0:
+ source_len = len(data_dict["system"]) + len(data_dict["user"])
+ return source_len
def get_target_len(self, data_dict):
- return len(data_dict["assistant"])
+ return 0
if __name__ == "__main__":
--
Gitblit v1.9.1