Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.

examples/industrial_data_pretraining/sense_voice/demo.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/FunAudioLLM/SenseVoice). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+from funasr import AutoModel
+from funasr.utils.postprocess_utils import rich_transcription_postprocess
+
+model_dir = "iic/SenseVoiceSmall"
+
+
+model = AutoModel(
+    model=model_dir,
+    vad_model="fsmn-vad",
+    vad_kwargs={"max_single_segment_time": 30000},
+    device="cuda:0",
+)
+
+# en
+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,
+)
+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)
+
+# zh
+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,
+)
+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",  # "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)
+
+# ja
+res = model.generate(
+    input=f"{model.model_path}/example/ja.mp3",
+    cache={},
+    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)
+
+
+# ko
+res = model.generate(
+    input=f"{model.model_path}/example/ko.mp3",
+    cache={},
+    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)