From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
examples/industrial_data_pretraining/sense_voice/demo.py | 40 +++++++++++++++++++++++++++++++++++-----
1 files changed, 35 insertions(+), 5 deletions(-)
diff --git a/examples/industrial_data_pretraining/sense_voice/demo.py b/examples/industrial_data_pretraining/sense_voice/demo.py
index b8a10a8..7a15cf2 100644
--- a/examples/industrial_data_pretraining/sense_voice/demo.py
+++ b/examples/industrial_data_pretraining/sense_voice/demo.py
@@ -20,12 +20,27 @@
res = model.generate(
input=f"{model.model_path}/example/en.mp3",
cache={},
- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
merge_length_s=15,
)
+text = rich_transcription_postprocess(res[0]["text"])
+print(text)
+
+# en with timestamp
+res = model.generate(
+ input=f"{model.model_path}/example/en.mp3",
+ cache={},
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
+ use_itn=True,
+ batch_size_s=60,
+ merge_vad=True, #
+ merge_length_s=15,
+ output_timestamp=True,
+)
+print(res)
text = rich_transcription_postprocess(res[0]["text"])
print(text)
@@ -33,7 +48,7 @@
res = model.generate(
input=f"{model.model_path}/example/zh.mp3",
cache={},
- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
@@ -42,11 +57,26 @@
text = rich_transcription_postprocess(res[0]["text"])
print(text)
+# zh with timestamp
+res = model.generate(
+ input=f"{model.model_path}/example/zh.mp3",
+ cache={},
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
+ use_itn=True,
+ batch_size_s=60,
+ merge_vad=True, #
+ merge_length_s=15,
+ output_timestamp=True,
+)
+print(res)
+text = rich_transcription_postprocess(res[0]["text"])
+print(text)
+
# yue
res = model.generate(
input=f"{model.model_path}/example/yue.mp3",
cache={},
- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
@@ -59,7 +89,7 @@
res = model.generate(
input=f"{model.model_path}/example/ja.mp3",
cache={},
- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
@@ -73,7 +103,7 @@
res = model.generate(
input=f"{model.model_path}/example/ko.mp3",
cache={},
- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
--
Gitblit v1.9.1