From 8b74979bd38c70c731e04b32308f2c9edeabdc37 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 七月 2024 13:57:51 +0800
Subject: [PATCH] sensevoice
---
funasr/auto/auto_model.py | 7 +++
examples/industrial_data_pretraining/sense_voice/demo.py | 70 +++++++++++++++++++++++++++++++---
2 files changed, 69 insertions(+), 8 deletions(-)
diff --git a/examples/industrial_data_pretraining/sense_voice/demo.py b/examples/industrial_data_pretraining/sense_voice/demo.py
index 1800d75..f10e54b 100644
--- a/examples/industrial_data_pretraining/sense_voice/demo.py
+++ b/examples/industrial_data_pretraining/sense_voice/demo.py
@@ -3,26 +3,82 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
# MIT License (https://opensource.org/licenses/MIT)
-import sys
+
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
-input_file = (
- "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
-)
+
model = AutoModel(
model=model_dir,
+ vad_model="fsmn-vad",
+ vad_kwargs={"max_single_segment_time": 30000},
+ device="cpu",
)
+# en
res = model.generate(
- input=input_file,
+ input=f"{model.model_path}/example/en.mp3",
cache={},
language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
- use_itn=False,
+ use_itn=True,
+ batch_size_s=60,
+ merge_vad=True, #
+ merge_length_s=15,
)
-
text = rich_transcription_postprocess(res[0]["text"])
+print(text)
+# zh
+res = model.generate(
+ input=f"{model.model_path}/example/zh.mp3",
+ cache={},
+ language="auto", # "zn", "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)
+
+# yue
+res = model.generate(
+ input=f"{model.model_path}/example/yue.mp3",
+ cache={},
+ language="auto", # "zn", "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)
+
+# ja
+res = model.generate(
+ input=f"{model.model_path}/example/ja.mp3",
+ cache={},
+ language="auto", # "zn", "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)
+
+
+# ko
+res = model.generate(
+ input=f"{model.model_path}/example/ko.mp3",
+ cache={},
+ language="auto", # "zn", "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)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 1c2d2e4..a82f6ed 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -339,7 +339,9 @@
# FIX(gcf): concat the vad clips for sense vocie model for better aed
if kwargs.get("merge_vad", False):
for i in range(len(res)):
- res[i]["value"] = merge_vad(res[i]["value"], kwargs.get("merge_length", 15000))
+ res[i]["value"] = merge_vad(
+ res[i]["value"], kwargs.get("merge_length_s", 15) * 1000
+ )
# step.2 compute asr model
model = self.model
@@ -380,6 +382,9 @@
if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
batch_size = max(batch_size, sorted_data[0][0][1] - sorted_data[0][0][0])
+ if kwargs["device"] == "cpu":
+ batch_size = 0
+
beg_idx = 0
beg_asr_total = time.time()
time_speech_total_per_sample = speech_lengths / 16000
--
Gitblit v1.9.1