mirror of
https://github.com/shirayu/whispering.git
synced 2024-06-02 21:39:28 +00:00
feat: add a resampling feature
This commit is contained in:
charles-zablit
parent
2dd2c6c036
commit
834e1c5807
48
poetry.lock
generated
48
poetry.lock
generated
|
|
@ -401,6 +401,22 @@ urllib3 = ">=1.21.1,<1.27"
|
|||
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
|
||||
use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
|
||||
|
||||
[[package]]
|
||||
name = "scipy"
|
||||
version = "1.9.3"
|
||||
description = "Fundamental algorithms for scientific computing in Python"
|
||||
category = "main"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
|
||||
[package.dependencies]
|
||||
numpy = ">=1.18.5,<1.26.0"
|
||||
|
||||
[package.extras]
|
||||
dev = ["flake8", "mypy", "pycodestyle", "typing_extensions"]
|
||||
doc = ["matplotlib (>2)", "numpydoc", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-panels (>=0.5.2)", "sphinx-tabs"]
|
||||
test = ["asv", "gmpy2", "mpmath", "pytest", "pytest-cov", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
|
||||
|
||||
[[package]]
|
||||
name = "snowballstemmer"
|
||||
version = "2.2.0"
|
||||
|
|
@ -610,7 +626,7 @@ resolved_reference = "d18e9ea5dd2ca57c697e8e55f9e654f06ede25d0"
|
|||
[metadata]
|
||||
lock-version = "1.1"
|
||||
python-versions = ">=3.8,<3.11"
|
||||
content-hash = "4be376481f536b81281e132b4b7a3a01d42b7639c3702b7ef9cc4a99908e51ab"
|
||||
content-hash = "46e1815ece308743e7df13e069b3acbfe9bcc4a9f7258a01ae60aacd8913319f"
|
||||
|
||||
[metadata.files]
|
||||
attrs = [
|
||||
|
|
@ -892,6 +908,13 @@ pyyaml = [
|
|||
{file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"},
|
||||
{file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d4b0ba9512519522b118090257be113b9468d804b19d63c71dbcf4a48fa32358"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:81957921f441d50af23654aa6c5e5eaf9b06aba7f0a19c18a538dc7ef291c5a1"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afa17f5bc4d1b10afd4466fd3a44dc0e245382deca5b3c353d8b757f9e3ecb8d"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dbad0e9d368bb989f4515da330b88a057617d16b6a8245084f1b05400f24609f"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:432557aa2c09802be39460360ddffd48156e30721f5e8d917f01d31694216782"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-win32.whl", hash = "sha256:bfaef573a63ba8923503d27530362590ff4f576c626d86a9fed95822a8255fd7"},
|
||||
{file = "PyYAML-6.0-cp311-cp311-win_amd64.whl", hash = "sha256:01b45c0191e6d66c470b6cf1b9531a771a83c1c4208272ead47a3ae4f2f603bf"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"},
|
||||
{file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"},
|
||||
|
|
@ -1013,6 +1036,29 @@ requests = [
|
|||
{file = "requests-2.28.1-py3-none-any.whl", hash = "sha256:8fefa2a1a1365bf5520aac41836fbee479da67864514bdb821f31ce07ce65349"},
|
||||
{file = "requests-2.28.1.tar.gz", hash = "sha256:7c5599b102feddaa661c826c56ab4fee28bfd17f5abca1ebbe3e7f19d7c97983"},
|
||||
]
|
||||
scipy = [
|
||||
{file = "scipy-1.9.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1884b66a54887e21addf9c16fb588720a8309a57b2e258ae1c7986d4444d3bc0"},
|
||||
{file = "scipy-1.9.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:83b89e9586c62e787f5012e8475fbb12185bafb996a03257e9675cd73d3736dd"},
|
||||
{file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a72d885fa44247f92743fc20732ae55564ff2a519e8302fb7e18717c5355a8b"},
|
||||
{file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d01e1dd7b15bd2449c8bfc6b7cc67d630700ed655654f0dfcf121600bad205c9"},
|
||||
{file = "scipy-1.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:68239b6aa6f9c593da8be1509a05cb7f9efe98b80f43a5861cd24c7557e98523"},
|
||||
{file = "scipy-1.9.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b41bc822679ad1c9a5f023bc93f6d0543129ca0f37c1ce294dd9d386f0a21096"},
|
||||
{file = "scipy-1.9.3-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:90453d2b93ea82a9f434e4e1cba043e779ff67b92f7a0e85d05d286a3625df3c"},
|
||||
{file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c06e62a390a9167da60bedd4575a14c1f58ca9dfde59830fc42e5197283dab"},
|
||||
{file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:abaf921531b5aeaafced90157db505e10345e45038c39e5d9b6c7922d68085cb"},
|
||||
{file = "scipy-1.9.3-cp311-cp311-win_amd64.whl", hash = "sha256:06d2e1b4c491dc7d8eacea139a1b0b295f74e1a1a0f704c375028f8320d16e31"},
|
||||
{file = "scipy-1.9.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:5a04cd7d0d3eff6ea4719371cbc44df31411862b9646db617c99718ff68d4840"},
|
||||
{file = "scipy-1.9.3-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:545c83ffb518094d8c9d83cce216c0c32f8c04aaf28b92cc8283eda0685162d5"},
|
||||
{file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d54222d7a3ba6022fdf5773931b5d7c56efe41ede7f7128c7b1637700409108"},
|
||||
{file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cff3a5295234037e39500d35316a4c5794739433528310e117b8a9a0c76d20fc"},
|
||||
{file = "scipy-1.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:2318bef588acc7a574f5bfdff9c172d0b1bf2c8143d9582e05f878e580a3781e"},
|
||||
{file = "scipy-1.9.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d644a64e174c16cb4b2e41dfea6af722053e83d066da7343f333a54dae9bc31c"},
|
||||
{file = "scipy-1.9.3-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:da8245491d73ed0a994ed9c2e380fd058ce2fa8a18da204681f2fe1f57f98f95"},
|
||||
{file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4db5b30849606a95dcf519763dd3ab6fe9bd91df49eba517359e450a7d80ce2e"},
|
||||
{file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c68db6b290cbd4049012990d7fe71a2abd9ffbe82c0056ebe0f01df8be5436b0"},
|
||||
{file = "scipy-1.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:5b88e6d91ad9d59478fafe92a7c757d00c59e3bdc3331be8ada76a4f8d683f58"},
|
||||
{file = "scipy-1.9.3.tar.gz", hash = "sha256:fbc5c05c85c1a02be77b1ff591087c83bc44579c6d2bd9fb798bb64ea5e1a027"},
|
||||
]
|
||||
snowballstemmer = [
|
||||
{file = "snowballstemmer-2.2.0-py2.py3-none-any.whl", hash = "sha256:c8e1716e83cc398ae16824e5572ae04e0d9fc2c6b985fb0f900f5f0c96ecba1a"},
|
||||
{file = "snowballstemmer-2.2.0.tar.gz", hash = "sha256:09b16deb8547d3412ad7b590689584cd0fe25ec8db3be37788be3810cbf19cb1"},
|
||||
|
|
|
|||
|
|
@ -20,6 +20,7 @@ websockets = "^10.3"
|
|||
tqdm = "*"
|
||||
torchaudio = "^0.12.1"
|
||||
PySoundFile = {version = "^0.9.0.post1", platform = "windows"}
|
||||
scipy = "^1.9.3"
|
||||
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
|
|
|
|||
24
whispering/resample.py
Normal file
24
whispering/resample.py
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
#!/usr/bin/env python3
|
||||
import numpy as np
|
||||
from scipy.interpolate import interp1d
|
||||
from whisper.audio import SAMPLE_RATE
|
||||
|
||||
|
||||
def resample(x: np.ndarray, source_sr: int) -> np.ndarray:
|
||||
"""Resample a numpy array to match the SAMPLE_RATE
|
||||
of Whisper (16 000 Hz).
|
||||
|
||||
Args:
|
||||
x (np.ndarray): Source numpy array
|
||||
source_sr (int): Source sample rate
|
||||
|
||||
Returns:
|
||||
np.ndarray: The resampled array
|
||||
"""
|
||||
|
||||
if source_sr == SAMPLE_RATE:
|
||||
return x
|
||||
factor = source_sr / SAMPLE_RATE
|
||||
n = int(np.ceil(x.size / factor))
|
||||
f = interp1d(np.linspace(0, 1, x.size), x, "linear")
|
||||
return f(np.linspace(0, 1, n))
|
||||
|
|
@ -49,6 +49,7 @@ class Context(BaseModel, arbitrary_types_allowed=True):
|
|||
max_nospeech_skip: int
|
||||
|
||||
data_type: str = "float32"
|
||||
source_sample_rate: int = 16000
|
||||
|
||||
|
||||
class ParsedChunk(BaseModel):
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@ from websockets.exceptions import ConnectionClosedOK
|
|||
|
||||
from whispering.schema import CURRENT_PROTOCOL_VERSION, Context
|
||||
from whispering.transcriber import WhisperStreamingTranscriber
|
||||
from whispering.resample import resample
|
||||
|
||||
logger = getLogger(__name__)
|
||||
|
||||
|
|
@ -77,6 +78,7 @@ async def serve_with_websocket_main(websocket):
|
|||
)
|
||||
return
|
||||
audio = np.frombuffer(message, dtype=np.dtype(ctx.data_type)).astype(np.float32)
|
||||
audio = resample(audio, ctx.source_sample_rate)
|
||||
for chunk in g_wsp.transcribe(
|
||||
audio=audio, # type: ignore
|
||||
ctx=ctx,
|
||||
|
|
|
|||
Loading…
Reference in a new issue