Add ReazonSpeech Japanese models (#630)

docs/source/conf.py

@@ -173,6 +173,7 @@ def get_version():
 .. _Node: https://nodejs.org/en
 .. _SenseVoice: https://github.com/FunAudioLLM/SenseVoice
 .. _LibriTTS-R: https://www.openslr.org/141/
+.. _ReazonSpeech: https://github.com/reazon-research/ReazonSpeech
 """
 
 

docs/source/onnx/pretrained_models/offline-transducer/code-zipformer/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01-int8.txt

@@ -0,0 +1,14 @@
+/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:375 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt --encoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.int8.onnx --decoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx --joiner=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.int8.onnx --num-threads=1 ./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/test_wavs/1.wav 
+
+OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.int8.onnx", decoder_filename="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx", joiner_filename="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.int8.onnx"), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), telespeech_ctc="", tokens="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="")
+Creating recognizer ...
+Started
+Done!
+
+./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/test_wavs/1.wav
+{"text": "気象庁は雪や路面の凍結による交通への影響暴風雪や高波に警戒するとともに雪崩や屋根からの落雪にも十分注意するよう呼びかけています", "timestamps": [0.00, 0.48, 0.64, 0.88, 1.24, 1.44, 1.80, 2.00, 2.12, 2.40, 2.56, 2.80, 2.96, 3.04, 3.44, 3.60, 3.88, 4.00, 4.28, 4.40, 4.76, 4.96, 5.20, 5.40, 5.72, 5.92, 6.20, 6.48, 6.64, 6.88, 6.96, 7.08, 7.28, 7.48, 7.64, 8.00, 8.16, 8.36, 8.68, 8.80, 9.04, 9.12, 9.28, 9.64, 9.80, 10.00, 10.16, 10.44, 10.64, 10.92, 11.04, 11.24, 11.36, 11.52, 11.60, 11.88, 11.92, 12.16, 12.28, 12.44, 12.64, 13.16, 13.20], "tokens":["気", "象", "庁", "は", "雪", "や", "路", "面", "の", "凍", "結", "に", "よ", "る", "交", "通", "へ", "の", "影", "響", "暴", "風", "雪", "や", "高", "波", "に", "警", "戒", "す", "る", "と", "と", "も", "に", "雪", "崩", "や", "屋", "根", "か", "ら", "の", "落", "雪", "に", "も", "十", "分", "注", "意", "す", "る", "よ", "う", "呼", "び", "か", "け", "て", "い", "ま", "す"], "words": []}
+----
+num threads: 1
+decoding method: greedy_search
+Elapsed seconds: 0.719 s
+Real time factor (RTF): 0.719 / 13.433 = 0.054

docs/source/onnx/pretrained_models/offline-transducer/code-zipformer/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.txt

@@ -0,0 +1,14 @@
+/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:375 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt --encoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.onnx --decoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx --joiner=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.onnx --num-threads=1 ./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/test_wavs/1.wav 
+
+OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.onnx", decoder_filename="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx", joiner_filename="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.onnx"), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), telespeech_ctc="", tokens="./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="")
+Creating recognizer ...
+Started
+Done!
+
+./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/test_wavs/1.wav
+{"text": "気象庁は雪や路面の凍結による交通への影響暴風雪や高波に警戒するとともに雪崩や屋根からの落雪にも十分注意するよう呼びかけています", "timestamps": [0.00, 0.48, 0.64, 0.88, 1.24, 1.44, 1.80, 2.00, 2.12, 2.40, 2.56, 2.80, 2.96, 3.04, 3.44, 3.60, 3.88, 4.00, 4.28, 4.40, 4.76, 4.96, 5.20, 5.40, 5.72, 5.92, 6.16, 6.48, 6.64, 6.88, 6.96, 7.08, 7.28, 7.48, 7.64, 8.00, 8.16, 8.36, 8.68, 8.80, 9.04, 9.12, 9.28, 9.64, 9.80, 10.00, 10.16, 10.44, 10.64, 10.92, 11.04, 11.24, 11.36, 11.52, 11.64, 11.88, 11.92, 12.16, 12.28, 12.44, 12.64, 13.16, 13.20], "tokens":["気", "象", "庁", "は", "雪", "や", "路", "面", "の", "凍", "結", "に", "よ", "る", "交", "通", "へ", "の", "影", "響", "暴", "風", "雪", "や", "高", "波", "に", "警", "戒", "す", "る", "と", "と", "も", "に", "雪", "崩", "や", "屋", "根", "か", "ら", "の", "落", "雪", "に", "も", "十", "分", "注", "意", "す", "る", "よ", "う", "呼", "び", "か", "け", "て", "い", "ま", "す"], "words": []}
+----
+num threads: 1
+decoding method: greedy_search
+Elapsed seconds: 1.101 s
+Real time factor (RTF): 1.101 / 13.433 = 0.082

docs/source/onnx/pretrained_models/offline-transducer/zipformer-transducer-models.rst

@@ -8,6 +8,164 @@ Zipformer-transducer-based Models
    Please refer to :ref:`install_sherpa_onnx` to install `sherpa-onnx`
    before you read this section.
 
+sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01 (Japanese, 日语)
+------------------------------------------------------------------
+
+This model is from `ReazonSpeech`_ and supports only Japanese.
+It is trained by 35k hours of data.
+
+The code for training the model can be found at
+`<https://github.com/k2-fsa/icefall/tree/master/egs/reazonspeech/ASR>`_
+
+Paper about the dataset is `<https://research.reazon.jp/_static/reazonspeech_nlp2023.pdf>`_
+
+In the following, we describe how to download it and use it with `sherpa-onnx`_.
+
+
+.. hint::
+
+   The original onnx model is from
+
+    `<https://huggingface.co/reazon-research/reazonspeech-k2-v2>`_
+
+Download the model
+~~~~~~~~~~~~~~~~~~
+
+Please use the following commands to download it.
+
+.. code-block:: bash
+
+   wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2
+
+   # For Chinese users, you can use the following mirror
+   # wget https://hub.nuaa.cf/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2
+
+   tar xvf sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2
+   rm sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2
+
+   ls -lh sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01
+
+You should see the following output:
+
+.. code-block:: bash
+
+  -rw-r--r--  1 fangjun  staff   1.2K Aug  1 18:32 README.md
+  -rw-r--r--  1 fangjun  staff   2.8M Aug  1 18:32 decoder-epoch-99-avg-1.int8.onnx
+  -rw-r--r--  1 fangjun  staff    11M Aug  1 18:32 decoder-epoch-99-avg-1.onnx
+  -rw-r--r--  1 fangjun  staff   148M Aug  1 18:32 encoder-epoch-99-avg-1.int8.onnx
+  -rw-r--r--  1 fangjun  staff   565M Aug  1 18:32 encoder-epoch-99-avg-1.onnx
+  -rw-r--r--  1 fangjun  staff   2.6M Aug  1 18:32 joiner-epoch-99-avg-1.int8.onnx
+  -rw-r--r--  1 fangjun  staff    10M Aug  1 18:32 joiner-epoch-99-avg-1.onnx
+  drwxr-xr-x  8 fangjun  staff   256B Aug  1 18:31 test_wavs
+  -rw-r--r--  1 fangjun  staff    45K Aug  1 18:32 tokens.txt
+
+Decode wave files
+~~~~~~~~~~~~~~~~~
+
+.. hint::
+
+   It supports decoding only wave files of a single channel with 16-bit
+   encoded samples, while the sampling rate does not need to be 16 kHz.
+
+fp32
+^^^^
+
+The following code shows how to use ``fp32`` models to decode wave files:
+
+.. code-block:: bash
+
+  cd /path/to/sherpa-onnx
+
+  ./build/bin/sherpa-onnx-offline \
+    --tokens=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt \
+    --encoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.onnx \
+    --decoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx \
+    --joiner=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.onnx \
+    --num-threads=1 \
+    ./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/test_wavs/1.wav
+
+.. note::
+
+   Please use ``./build/bin/Release/sherpa-onnx-offline.exe`` for Windows.
+
+.. caution::
+
+   If you use Windows and get encoding issues, please run:
+
+      .. code-block:: bash
+
+          CHCP 65001
+
+   in your commandline.
+
+You should see the following output:
+
+.. literalinclude:: ./code-zipformer/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.txt
+
+int8
+^^^^
+
+The following code shows how to use ``int8`` models to decode wave files:
+
+.. code-block:: bash
+
+  cd /path/to/sherpa-onnx
+
+  ./build/bin/sherpa-onnx-offline \
+    --tokens=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt \
+    --encoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.int8.onnx \
+    --decoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx \
+    --joiner=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.int8.onnx \
+    --num-threads=1 \
+    ./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/test_wavs/1.wav
+
+.. note::
+
+   Please use ``./build/bin/Release/sherpa-onnx-offline.exe`` for Windows.
+
+.. caution::
+
+   If you use Windows and get encoding issues, please run:
+
+      .. code-block:: bash
+
+          CHCP 65001
+
+   in your commandline.
+
+You should see the following output:
+
+.. literalinclude:: ./code-zipformer/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01-int8.txt
+
+Speech recognition from a microphone
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. code-block:: bash
+
+  cd /path/to/sherpa-onnx
+
+  ./build/bin/sherpa-onnx-microphone-offline \
+    --tokens=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt \
+    --encoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.int8.onnx \
+    --decoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx \
+    --joiner=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.int8.onnx
+
+Speech recognition from a microphone with VAD
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. code-block:: bash
+
+  cd /path/to/sherpa-onnx
+
+  wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
+
+  ./build/bin/sherpa-onnx-vad-microphone-offline-asr \
+    --silero-vad-model=./silero_vad.onnx \
+    --tokens=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/tokens.txt \
+    --encoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/encoder-epoch-99-avg-1.int8.onnx \
+    --decoder=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/decoder-epoch-99-avg-1.onnx \
+    --joiner=./sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01/joiner-epoch-99-avg-1.int8.onnx
+
 sherpa-onnx-zipformer-korean-2024-06-24 (Korean, 韩语)
 ------------------------------------------------------------
 

docs/source/onnx/sense-voice/python-api.rst

@@ -376,7 +376,7 @@ Please visit `<http://localhost:6006>`_.
     - Incorrect/Wrong address: `<http://a.b.c.d:6006>`_
     - Incorrect/Wrong address: `<https://a.b.c.d:6006>`_
 
-After starting you browser, you should see the following page:
+After starting the browser, you should see the following page:
 
   .. image:: ./pic/python-websocket/client-1.jpg
      :align: center