From 94de39dde2e616a01683c518023d0fab72b4e103 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 22:21:50 +0800
Subject: [PATCH] aishell example
---
tests/test_asr_inference_pipeline.py | 107 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 106 insertions(+), 1 deletions(-)
diff --git a/tests/test_asr_inference_pipeline.py b/tests/test_asr_inference_pipeline.py
index a36563e..f68f29b 100644
--- a/tests/test_asr_inference_pipeline.py
+++ b/tests/test_asr_inference_pipeline.py
@@ -43,6 +43,7 @@
rec_result = inference_pipeline(
audio_in='https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav')
logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "姣忎竴澶╅兘瑕佸揩涔愬枖"
def test_paraformer(self):
inference_pipeline = pipeline(
@@ -51,6 +52,7 @@
rec_result = inference_pipeline(
audio_in='https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav')
logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "姣忎竴澶╅兘瑕佸揩涔愬枖"
class TestMfccaInferencePipelines(unittest.TestCase):
@@ -65,7 +67,7 @@
model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
model_revision='v3.0.0')
rec_result = inference_pipeline(
- audio_in='16:32https://pre.modelscope.cn/api/v1/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/repo?Revision=master&FilePath=example/asr_example_mc.wav')
+ audio_in='https://pre.modelscope.cn/api/v1/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/repo?Revision=master&FilePath=example/asr_example_mc.wav')
logger.info("asr inference result: {0}".format(rec_result))
@@ -85,6 +87,7 @@
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav')
logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "鍥藉姟闄㈠彂灞曠爺绌朵腑蹇冨競鍦虹粡娴庣爺绌舵墍鍓墍闀块倱閮佹澗璁や负"
def test_paraformer_large_aishell1(self):
inference_pipeline = pipeline(
@@ -93,6 +96,7 @@
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
def test_paraformer_large_aishell2(self):
inference_pipeline = pipeline(
@@ -101,6 +105,7 @@
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
def test_paraformer_large_common(self):
inference_pipeline = pipeline(
@@ -109,6 +114,33 @@
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
+
+ def test_paraformer_large_online_common(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+ model_revision='v1.0.6',
+ update_model=False,
+ mode="paraformer_fake_streaming"
+ )
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+ logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
+
+ def test_paraformer_online_common(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
+ model_revision='v1.0.6',
+ update_model=False,
+ mode="paraformer_fake_streaming"
+ )
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+ logger.info("asr inference result: {0}".format(rec_result))
+ assert rec_result["text"] == "娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�"
def test_paraformer_tiny_commandword(self):
inference_pipeline = pipeline(
@@ -395,6 +427,79 @@
param_dict={"decoding_model": "normal"})
logger.info("asr inference result: {0}".format(rec_result))
+ def test_uniasr_2pass_vi_common_offline(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-offline')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav',
+ param_dict={"decoding_model": "offline"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_vi_common_online(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav',
+ param_dict={"decoding_model": "normal"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_zhcn_8k_common_vocab3445_offline(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
+ param_dict={"decoding_model": "offline"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_zhcn_8k_common_vocab3445_online(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
+ param_dict={"decoding_model": "normal"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_zhcn_8k_common_vocab8358_offline(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-offline')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
+ param_dict={"decoding_model": "offline"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_zhcn_8k_common_vocab8358_online(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-online')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
+ param_dict={"decoding_model": "normal"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_zhcn_16k_common_vocab8358_offline(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
+ param_dict={"decoding_model": "offline"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+ def test_uniasr_2pass_zhcn_16k_common_vocab8358_online(self):
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online')
+ rec_result = inference_pipeline(
+ audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
+ param_dict={"decoding_model": "normal"})
+ logger.info("asr inference result: {0}".format(rec_result))
+
+
if __name__ == '__main__':
unittest.main()
--
Gitblit v1.9.1