msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

fix file name (#3895)

Browse Source
pull/3897/head
zxcd 10 months ago committed by GitHub
parent be7373326c
commit 89bfd44293
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File

16
paddlespeech/s2t/models/whisper/__init__.py
Unescape View File

@ -2,11 +2,11 @@
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved. # Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
# #
# Modified from OpenAI Whisper 2022 (https://github.com/openai/whisper/whisper/__init__.py) # Modified from OpenAI Whisper 2022 (https://github.com/openai/whisper/whisper/__init__.py)
from paddlespeech.s2t.models.whisper.whipser import decode from paddlespeech.s2t.models.whisper.whisper import decode
from paddlespeech.s2t.models.whisper.whipser import DecodingOptions from paddlespeech.s2t.models.whisper.whisper import DecodingOptions
from paddlespeech.s2t.models.whisper.whipser import DecodingResult from paddlespeech.s2t.models.whisper.whisper import DecodingResult
from paddlespeech.s2t.models.whisper.whipser import detect_language from paddlespeech.s2t.models.whisper.whisper import detect_language
from paddlespeech.s2t.models.whisper.whipser import log_mel_spectrogram from paddlespeech.s2t.models.whisper.whisper import log_mel_spectrogram
from paddlespeech.s2t.models.whisper.whipser import ModelDimensions from paddlespeech.s2t.models.whisper.whisper import ModelDimensions
from paddlespeech.s2t.models.whisper.whipser import transcribe from paddlespeech.s2t.models.whisper.whisper import transcribe
from paddlespeech.s2t.models.whisper.whipser import Whisper from paddlespeech.s2t.models.whisper.whisper import Whisper

12
paddlespeech/s2t/models/whisper/whipser.py → paddlespeech/s2t/models/whisper/whisper.py
Unescape View File

@ -17,11 +17,12 @@ from typing import Union
import numpy as np import numpy as np
import paddle import paddle
import paddle.nn.functional as F import paddle.nn.functional as F
import paddlespeech.s2t.modules.align as paddlespeech_nn
import soundfile import soundfile
import tqdm import tqdm
from paddle import nn from paddle import nn
from paddle.distribution import Categorical from paddle.distribution import Categorical
import paddlespeech.s2t.modules.align as paddlespeech_nn
from paddlespeech.s2t.models.whisper import utils from paddlespeech.s2t.models.whisper import utils
from paddlespeech.s2t.models.whisper.tokenizer import get_tokenizer from paddlespeech.s2t.models.whisper.tokenizer import get_tokenizer
from paddlespeech.s2t.models.whisper.tokenizer import LANGUAGES from paddlespeech.s2t.models.whisper.tokenizer import LANGUAGES
@ -475,8 +476,8 @@ def transcribe(
if dtype == np.float32: if dtype == np.float32:
decode_options["fp16"] = False decode_options["fp16"] = False
if decode_options.get( if decode_options.get("language") == 'None' or decode_options.get(
"language") == 'None' or decode_options.get("language", None) is None: "language", None) is None:
if not model.is_multilingual: if not model.is_multilingual:
decode_options["language"] = "en" decode_options["language"] = "en"
else: else:
@ -1206,8 +1207,9 @@ class DecodingTask:
DecodingResult( DecodingResult(
audio_features=features, audio_features=features,
language=language, language=language,
language_probs=probs) for features, language, probs in language_probs=probs)
zip(audio_features, languages, language_probs) for features, language, probs in zip(audio_features, languages,
language_probs)
] ]
# repeat the audio & text tensors by the group size, for beam search or best-of-n sampling # repeat the audio & text tensors by the group size, for beam search or best-of-n sampling
Write Preview
Loading…
Cancel
Save