Unduh sub to audio - Unduh Kode Sumber sub to audio

Subtitle ke audio

Subtitle ke audio, menghasilkan audio/pidato dari file subtitle apa pun menggunakan coqui-ai tts dan menyinkronkan waktu audio sesuai dengan waktu subtitle.

Demo:

Dependensi

ffmpeg, pydub, librosa, coqui-ai tts, ffmpeg-python

Instalasi

pip install TTS
pip install git+https://github.com/bnsantoso/sub-to-audio

pip install TTS
pip install subtoaudio

FFMPEG di Linux

apt-get install ffmpeg

Contoh penggunaan

Penggunaan dasar sangat mirip untuk coqui-ai tts, Anda dapat memeriksa dokumentasinya dan <lang-iso_code>.

Catatan: Gunakan subtitle yang tidak tumpang tindih dengan karakter optimal per detik / cps untuk hasil terbaik

Catatan: Gunakan perangkat lunak seperti Aegisub untuk mengedit subtitle Anda

 from subtoaudio import SubToAudio

# list all model
SubToAudio (). coqui_model ()

# get model index
model = SubToAudio (). coqui_model ()[ 1 ]

# The code will output 'yoursubtitle.wav' in the current directory.
sub = SubToAudio ( model_name = model )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle )

# you can choose 1100 different language using fairseq model
sub = SubToAudio ( fairseq_language = '<lang-iso_code>' )
subtitle = sub . subtitle ( "yoursubtitle.ass" )
sub . convert_to_audio ( sub_data = subtitle ) 

# specify model name
sub = SubToAudio ( model_name = "tts_models/multilingual/multi-dataset/your_tts" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , output_path = "subtitle.wav" )

# specify model and config path
sub = SubToAudio ( model_path = "path/to/your/model.pth" config_path = "config/path.json" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle )

# speaker=tts.speakers[0] or None if model doesnt have multiple speakers
# language=tts.languages[0] or None if doesnt have multiple languages

# list speaker
sub . speakers ()
speaker1 = sub . speakers ()[ 1 ]

# list languages
sub . languages ()
langu = sub . languages ()[ 0 ]

sub = SubToAudio ( model_name = "tts_models/multilingual/multi-dataset/your_tts" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , language = langu , speaker = speaker1 , output_path = "subtitle.wav" )

# Save temporary audio to current folder
sub = SubToAudio ( model_name = "tts_models/multilingual/multi-dataset/your_tts" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , output_path = "subtitle.wav" , save_temp = True )

Konversi suara

Untuk menggunakan metode konversi suara, Anda harus lulus voice_conversion:bool dan speaker_wav:str paramater di self.convert_to_audio . Konversi suara tidak dapat berjalan jika model Anda memiliki banyak speaker.

 from subtoaudio import SubToAudio

sub = SubToAudio ( fairseq_language = "eng" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , voice_conversion = True , speaker_wav = "voice.wav" , language = "en" )

Coqui Studio API

Untuk menggunakan API Coqui Studio Anda harus mengkonfigurasi variabel lingkungan Coqui_studio_Token.

 import os

os . environ [ 'COQUI_STUDIO_TOKEN' ] = # yourapi

Setelah set token Anda, Anda bisa mendapatkan model coqui studio, Anda dapat mengikuti nama ini konvensi coqui_studio/en/<studio_speaker_name>/coqui_studio

 from subtoaudio import SubToAudio

sub = SubToAudio ( model_name = "coqui_studio/en/Torcull Diarmuid/coqui_studio" , progress_bar = False )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , output_path = "subtitle.wav" , save_temp = True )

# use emotion paramater and speed paramater
sub . convert_to_audio ( sub_data = subtitle , output_path = "subtitle.wav" , emotion = "Happy" , speed = 1.5 )

Mode tempo

Gunakan parameter tempo_mode untuk mempercepat audio. Ada tiga mode tempo:

tempo_mode="all" : Ini mempercepat semua audio. Gunakan tempo_speed=float untuk menentukan kecepatan.
tempo_mode="overflow" : Ini mempercepat audio agar sesuai dengan total durasi subtitle ditambah durasi kosong sebelum subtitle berikutnya muncul. 'tempo_limit' akan membatasi peningkatan kecepatan selama overflow.
tempo_mode="precise" : Ini mempercepat audio agar sesuai dengan durasi subtitle yang muncul. "

 from subtoaudio import SubToAudio

# Speed up tempo or speech rate
sub = SubToAudio ( model_name = "tts_models/de/thorsten/tacotron2-DDC" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "all" , tempo_speed = 1.3 )

# Change the tempo or speech rate of all audio files , default is 1.2
sub = SubToAudio ( "tts_models/multilingual/multi-dataset/xtts_v1" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "all" , tempo_speed = 1.3 )

# Change tempo or speech rate to audio that doesn't match the subtitle duration
sub = SubToAudio ( fairseq_language = "ind" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "overflow" )

# Limit tempo speed on the overflow mode 
sub = SubToAudio ( fairseq_language = "ind" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "overflow" , tempo_limit = 1.2 )

# Match audio length to subtitle duration
sub = SubToAudio ( fairseq_language = "ind" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "precise" )

Mode shift

Parameter shift_mode akan menggeser audio yang tidak cocok dengan durasi subtitle.

shift_mode="right" : Shift Audio Time ke kanan dan mencegah audio tumpang tindih.
shift_mode="left" : Shift audio ke kiri dan mencegah audio tumpang tindih, tetapi berhati -hatilah terhadap ruang terbatas di sisi kiri, karena beberapa audio mungkin hilang.
shift_mode="interpose" : SHIFT audio ke posisi menengah dan mencegah kanan dan kiri audio tumpang tindih. (Catatan: Mode ini bisa kikuk, jadi gunakan dengan hati -hati.)
shift_mode="left-overlap" : shift waktu audio ke kiri, memungkinkan tumpang tindih.
shift_mode="interpose-overlap" : shift audio ke posisi menengah, memungkinkan tumpang tindih.
shift_limit=int or "str" : Batasi shift audio, gunakan integer untuk milidetik atau string seperti 2.5s untuk kedua

 from subtoaudio import SubToAudio

# shift mode with limit of 2 second to the right.

sub = SubToAudio ( fairseq_language = "vie" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = sub , tempo_mode = "overflow" , shift_mode = "right" , limit_shift = "2s" )

# shift audio to left position or, time before next subtitle appear

sub = SubToAudio ( fairseq_language = "fra" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = sub , shift_mode = "left-overlap" )

# shift to left, and limit shift only 1 sec.
sub = SubToAudio ( fairseq_language = "ind" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = sub , shift_mode = "left" , shift_limit = 1000 ) # 1000 = 1s

Contoh kulit kayu dan kura -kura

 from subtoaudio import SubToAudio

#  Random Speaker will give you weird result when using bark model with SubToAudio

# Bark random
sub = SubToAudio ( "tts_models/multilingual/multi-dataset/bark" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "overflow" )

# Tortoise random
sub = SubToAudio ( "tts_models/en/multi-dataset/tortoise-v2" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , shift_mode = "overflow" , preset = "fast" )

#  To use voice clone you need voice_dir and speaker paramater
#  Voice Clone expecting .wav or .npz file inside folder speaker_1
#  voice/speaker_1/hana.wav or voice/speaker_1/hana.npz
#  if your speaker folder only have .wav file, it will generate .npz file after you runing it.

sub = SubToAudio ( "tts_models/multilingual/multi-dataset/bark" )
subtitle = sub . subtitle ( "yoursubtitle.srt" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "overflow" , voice_dir = "voice/" , speaker = "speaker_1" )

# same with bark, the folder structure like this 'voice/speaker2/ron.wav'
sub = SubToAudio ( "tts_models/en/multi-dataset/tortoise-v2" )
subtitle = sub . subtitle ( "yoursubtitle.ass" )
sub . convert_to_audio ( sub_data = subtitle , tempo_mode = "overflow" , voice_dir = "voice/" , speaker = "speaker2" )