ReazonSpeech Nemo とは

2024年9月17日現在優れた日本語音声認識（ASR）モデルの一つ
公式ドキュメント
https://research.reazon.jp/projects/ReazonSpeech/quickstart.html
Linux 推奨

使い方

まずはモデルをダウンロード

git lfs install
git clone https://huggingface.co/reazon-research/reazonspeech-nemo-v2

cd reazonspeech-nemo-v2
ls  # ダウンロードしたファイルが表示されます
touch requirements.txt # ファイル新規作成 以下を記入
touch test.py # 以下を記入
pip install -r requirements.txt # 仮想環境でインストール
python test.py

requirements.txt

nemo_toolkit[asr]==2.0.0rc0
git+https://github.com/reazon-research/ReazonSpeech@v2.0.0#egg=reazonspeech-nemo-asr&subdirectory=pkg/nemo-asr
datasets
soundfile
librosa
fastapi
uvicorn
numpy<2
huggingface_hub==0.22.0
torch>=1.12.0
torchaudio>=0.9.0
cuda-python

test.py

# huggingface サンプルコードそのまま
# speech.wavを用意してね

from reazonspeech.nemo.asr import load_model, transcribe, audio_from_path

audio = audio_from_path("speech.wav")
model = load_model(device='cuda')
ret = transcribe(model, audio)
print(ret.text)

server.py

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
import os
from reazonspeech.nemo.asr import load_model, transcribe, audio_from_path
import uvicorn
class TranscribeRequest(BaseModel):
    filepath: str

app = FastAPI()

# Load model once
model = load_model(device='cuda')

@app.post("/transcribe/")
async def transcribe_audio(request: TranscribeRequest):
    filepath = request.filepath
    if not os.path.exists(filepath):
        raise HTTPException(status_code=400, detail="File does not exist")

    try:
        audio = audio_from_path(filepath)
        result = transcribe(model, audio)
        return {"text": result.text}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

if __name__ == '__main__':
    uvicorn.run(app, host='0.0.0.0', port=5001)

参考用

$ pip list

list
Package                  Version
------------------------ ------------
absl-py                  2.1.0
aiohappyeyeballs         2.4.0
aiohttp                  3.10.5
aiosignal                1.3.1
annotated-types          0.7.0
antlr4-python3-runtime   4.9.3
anyio                    4.4.0
asttokens                2.4.1
async-timeout            4.0.3
attrs                    24.2.0
audioread                3.0.1
braceexpand              0.1.7
certifi                  2024.8.30
cffi                     1.17.1
charset-normalizer       3.3.2
click                    8.1.7
cloudpickle              3.0.0
comm                     0.2.2
contourpy                1.3.0
cycler                   0.12.1
cytoolz                  0.12.3
datasets                 3.0.0
decorator                5.1.1
dill                     0.3.8
distance                 0.1.3
docker-pycreds           0.4.0
docopt                   0.6.2
editdistance             0.8.1
einops                   0.8.0
exceptiongroup           1.2.2
executing                2.1.0
fastapi                  0.114.2
fiddle                   0.3.0
filelock                 3.16.0
fonttools                4.53.1
frozenlist               1.4.1
fsspec                   2024.6.1
future                   1.0.0
g2p-en                   2.1.0
gitdb                    4.0.11
gitpython                3.1.43
graphviz                 0.20.3
grpcio                   1.66.1
h11                      0.14.0
huggingface-hub          0.22.0
hydra-core               1.3.2
idna                     3.10
inflect                  7.4.0
intervaltree             3.1.0
ipython                  8.27.0
ipywidgets               8.1.5
jedi                     0.19.1
jinja2                   3.1.4
jiwer                    3.0.4
joblib                   1.4.2
jupyterlab-widgets       3.0.13
kaldi-python-io          1.2.2
kaldiio                  2.18.0
kiwisolver               1.4.7
lazy-loader              0.4
levenshtein              0.25.1
lhotse                   1.27.0
libcst                   1.4.0
librosa                  0.10.2.post1
lightning-utilities      0.11.7
lilcom                   1.8.0
llvmlite                 0.43.0
loguru                   0.7.2
markdown                 3.7
markdown-it-py           3.0.0
markupsafe               2.1.5
marshmallow              3.22.0
matplotlib               3.9.2
matplotlib-inline        0.1.7
mdurl                    0.1.2
more-itertools           10.5.0
mpmath                   1.3.0
msgpack                  1.1.0
multidict                6.1.0
multiprocess             0.70.16
nemo-toolkit             2.0.0rc0
networkx                 3.3
nltk                     3.9.1
numba                    0.60.0
numpy                    1.26.4
nvidia-cublas-cu12       12.1.3.1
nvidia-cuda-cupti-cu12   12.1.105
nvidia-cuda-nvrtc-cu12   12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12        9.1.0.70
nvidia-cufft-cu12        11.0.2.54
nvidia-curand-cu12       10.3.2.106
nvidia-cusolver-cu12     11.4.5.107
nvidia-cusparse-cu12     12.1.0.106
nvidia-nccl-cu12         2.20.5
nvidia-nvjitlink-cu12    12.6.68
nvidia-nvtx-cu12         12.1.105
omegaconf                2.3.0
onnx                     1.16.2
packaging                24.1
pandas                   2.2.2
parso                    0.8.4
pexpect                  4.9.0
pillow                   10.4.0
plac                     1.4.3
platformdirs             4.3.3
pooch                    1.8.2
prompt-toolkit           3.0.47
protobuf                 5.28.1
psutil                   6.0.0
ptyprocess               0.7.0
pure-eval                0.2.3
pyannote-core            5.0.0
pyannote-database        5.1.0
pyannote-metrics         3.2.1
pyarrow                  17.0.0
pybind11                 2.13.6
pycparser                2.22
pydantic                 2.9.1
pydantic-core            2.23.3
pydub                    0.25.1
pygments                 2.18.0
pyloudnorm               0.1.1
pyparsing                3.1.4
python-dateutil          2.9.0.post0
pytorch-lightning        2.4.0
pytz                     2024.2
pyyaml                   6.0.2
rapidfuzz                3.9.7
reazonspeech-nemo-asr    2.0.0
regex                    2024.9.11
requests                 2.32.3
resampy                  0.4.3
rich                     13.8.1
ruamel-yaml              0.18.6
ruamel-yaml-clib         0.2.8
sacremoses               0.1.1
safetensors              0.4.5
scikit-learn             1.5.2
scipy                    1.14.1
sentencepiece            0.2.0
sentry-sdk               2.14.0
setproctitle             1.3.3
setuptools               75.1.0
shellingham              1.5.4
six                      1.16.0
smmap                    5.0.1
sniffio                  1.3.1
sortedcontainers         2.4.0
soundfile                0.12.1
sox                      1.5.0
soxr                     0.5.0.post1
stack-data               0.6.3
starlette                0.38.5
sympy                    1.13.2
tabulate                 0.9.0
tensorboard              2.17.1
tensorboard-data-server  0.7.2
termcolor                2.4.0
text-unidecode           1.3
texterrors               0.5.1
threadpoolctl            3.5.0
tokenizers               0.19.1
toolz                    0.12.1
torch                    2.4.1
torchmetrics             1.4.2
tqdm                     4.66.5
traitlets                5.14.3
transformers             4.40.2
triton                   3.0.0
typeguard                4.3.0
typer                    0.12.5
typing-extensions        4.12.2
tzdata                   2024.1
urllib3                  2.2.3
uvicorn                  0.30.6
wandb                    0.18.0
wcwidth                  0.2.13
webdataset               0.2.100
werkzeug                 3.0.4
wget                     3.2
widgetsnbextension       4.0.13
wrapt                    1.16.0
xxhash                   3.5.0
yarl                     1.11.1