Pi79 d dl Z d dlmZmZ d dlmZ d dlmZ d dlm Z m
Z
m Z m Z m
Z
d dlZd dlZddlmZ ddlmZ dd lmZ dd
lmZmZ dd lm Z m Z e r d d l m Z d
dl m!Z! e G d d Z"ddde#fdZ$dS ) N) dataclassfield)BytesIO)Path)
TYPE_CHECKINGAnyClassVarOptionalUnion )config)DownloadConfig)
array_cast)
is_local_pathxopen)no_op_if_value_is_nullstring_to_dict AudioDecoder ) FeatureTypec R e Zd ZU dZdZee ed< dZe ed< dZ
ee ed< dZ ee ed< e dd Z
ee ed
< d Zee ed < ej ej ej d
Zee ed< e d dd Zeed< d Zdeeeee df de fdZ d de dee eeee df f ddfdZ dede edf f fdZ deej ej! f dej! fdZ"d dej! dej! fd Z#dS ) Audioa
Audio [`Feature`] to extract audio data from an audio file.
Input: The Audio feature accepts as input:
- A `str`: Absolute path to the audio file (i.e. random access is allowed).
- A `pathlib.Path`: path to the audio file (i.e. random access is allowed).
- A `dict` with the keys:
- `path`: String with relative path of the audio file to the archive file.
- `bytes`: Bytes content of the audio file.
This is useful for parquet or webdataset files which embed audio files.
- A `dict` with the keys:
- `array`: Array containing the audio sample
- `sampling_rate`: Integer corresponding to the sampling rate of the audio sample.
- A `torchcodec.decoders.AudioDecoder`: torchcodec audio decoder object.
Output: The Audio features output data as `torchcodec.decoders.AudioDecoder` objects, with additional keys:
- `array`: Array containing the audio sample
- `sampling_rate`: Integer corresponding to the sampling rate of the audio sample.
Args:
sampling_rate (`int`, *optional*):
Target sampling rate. If `None`, the native sampling rate is used.
num_channels (`int`, *optional*):
The desired number of channels of the samples. By default, the number of channels of the source is used.
Audio decoding will return samples with shape (num_channels, num_samples)
Currently `None` (number of channels of the source, default), `1` (mono) or `2` (stereo) channels are supported.
The `num_channels` argument is passed to `torchcodec.decoders.AudioDecoder`.
decode (`bool`, defaults to `True`):
Whether to decode the audio data. If `False`,
returns the underlying dictionary in the format `{"path": audio_path, "bytes": audio_bytes}`.
stream_index (`int`, *optional*):
The streaming index to use from the file. If `None` defaults to the "best" index.
Example:
```py
>>> from datasets import load_dataset, Audio
>>> ds = load_dataset("PolyAI/minds14", name="en-US", split="train")
>>> ds = ds.cast_column("audio", Audio(sampling_rate=44100, num_channels=2))
>>> ds[0]["audio"]
>>> audio = ds[0]["audio"]
>>> audio.get_samples_played_in_range(0, 10)
AudioSamples:
data (shape): torch.Size([2, 110592])
pts_seconds: 0.0
duration_seconds: 2.507755102040816
sample_rate: 44100
```
N
sampling_rateTdecode num_channels stream_indexF)defaultrepriddictdtypebytespathpa_type)r initr _typec | j S N)r& )selfs k/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/datasets/features/audio.py__call__zAudio.__call__] s
| valuer returnc ddl }ddlm} n"# t $ r}t d |d}~ww xY w|t d t
j rddlm} nd}t |t rd|dS t |t r$dt | dS t |t t f r|ddS | t || rt | S d|v rt! } || |d t& j |d
|d | j | ddS | d
}t2 j |d
rW|d
d r#| d t; d | d rGt' j |d t& j t& j dz }n=t' j |d
dd t& j dz }t! } || | |d
|d | j | ddS d| d
dS | d | d
+| d | d
dS t d| d )zEncode example into a format for Arrow.
Args:
value (`str`, `bytes`,`bytearray`,`dict`, `AudioDecoder`):
Data passed as input to Audio feature.
Returns:
`dict`
r N AudioEncoderOlPPP #__ . .== =
YYv
*rw~~eFm/L/L
*V}%%e,,
B99_--5"#ghhh99W%% k"$-gbh"O"O"O"V"VWYWa"b"bej"jKK"$)E&M3"O"O"O"V"VWYWa"b"bej"jK U - -k : :oH^___ll5t7H m "( !2!2DAAA!%uyy/@/@AAA
YYw
+uyy/@/@/L "YYw / /69J9JKK K phmppp
s
,',token_per_repo_idc F t j rddlm} nt d | j st
d |d |d |d fn |d df\ }}||t d| d |.t | r ||| j | j
| j
}n||pi }| d d }|
t j r t j n t j }t# || } | | | d
nd}
t' |
} t) |d| } || | j | j
| j
}n ||| j | j
| j
}||d|_ ||j _ |S )a, Decode example audio file into audio data.
Args:
value (`dict`):
A dictionary with keys:
- `path`: String with relative audio file path.
- `bytes`: Bytes of the audio file.
token_per_repo_id (`dict`, *optional*):
To access and decode
audio files from private repositories on the Hub, you can pass
a dictionary repo_id (`str`) -> token (`bool` or `str`)
Returns:
`torchcodec.decoders.AudioDecoder`
r r zw 9SuV}eGn55Z_`fZgimYn e z&Audio.cast_storage.. s3 vvv!am''***vvvr. F)zero_copy_onlyr )patypes is_stringr r5 lenrx StructArray from_arraysis_null is_binaryry is_structget_all_field_indicesto_numpyget_field_indexr r r& )r+ r| bytes_array
path_arrays r, cast_storagezAudio.cast_storage sk $ 8 gl + + w (D6CLL#8ry{{KKKKn00+w1G'SYIZahapaparar0ssGG
X
-
- w4&3w<<"7bikkJJJJn00':1FRXHY`g`o`o`q`q0rrGG
X
-
-
w',2T2TU\2]2]
whvvwO_O_otO_OuOuvvv GG X
-
- w|++G4499 %mmG 4 4 hvG '<29;; O O O |++F33q88 $]]6 2 2
Xtfs7||&;")++ N N N
n00+z1JWV\L]dkdsdsdudu0vvG'4<000r. c i t fd t j fd| D t j }t j d | d D t j }t j ||gddg| }t || j S ) a8 Embed audio files into the Arrow array.
Args:
storage (`pa.StructArray`):
PyArrow array to embed.
Returns:
`pa.StructArray`: Array in the Audio arrow storage type, that is
`pa.struct({"bytes": pa.binary(), "path": pa.string()})`.
Nc | d d }| t j r t j n t j }t
|| }| |d nd }t | }t | d| 5 }|
cd d d S # 1 swxY w Y d S )Nr_ r` ra rb rd re ) ri rj r
rk rl rm r rQ r r read)r% rq rr rs rc rf rt r] s r,
path_to_bytesz*Audio.embed_storage..path_to_bytes s D))"-J+5+@+@AS+T+Tv''Z`Zv
!/z7 C C K\Kh%))*;I*FGGGnrE ,5 9 9 9OtT?CCC
qvvxx
s %CC
C
c Z g | ]'}|!|d |d n |d nd (S )Nr$ r% )r r r s r, r z'Audio.embed_storage..- sU
UVTaQwZ-? qy)))QwZZgk
r. r~ c T g | ]%}| t j | nd &S r* )rR r% basename)r r% s r, r z'Audio.embed_storage..4 s2 p p pdt'7RW
d
#
#
#T p p pr. r% r$ r ) r r r5 to_pylistrx r ry r r r r r& )r+ r| r] r r r s ` @r,
embed_storagezAudio.embed_storage s $ "
h
**,,
X p pgmm\bNcNcNmNmNoNo p p p
.,,k:-FRXHY`k`s`s`u`u,vv'4<000r. r* )$__name__
__module__ __qualname____doc__r r
int__annotations__r boolr r r r rG r" r r structrx ry r& r r( r- r r$ rI r! r\ ru r{ StringArrayr r r r r. r, r r s+ 8 8t $(M8C='''FD"&L(3-&&&"&L(3-&&& d777B
777!E8C=!!! &RYibikk'R'R S SGXc]SSSwU???E3??? BE#ui~*U$V B[_ B B B BJ ]a9 99.6tCsDRVAWr s ( ( ( ( ( ( ( ( @ @ @ @ @ @ @ @ @ @ @ @ @ @ 5 5 5 5 5 5 3 3 3 3 3 3 3 3 C C C C C C C C &000000%%%%%% `1 `1 `1 `1 `1 `1 `1 `1F :> :d : : : : : :r.