mirror of
https://github.com/wassname/TTS.git
synced 2026-08-21 11:11:30 +08:00
a3d5801c44
* initial commit * Tortoise inference * revert path change * style fix * remove accidental remove * style fixes * style fixes * removed unwanted assests and deps * remove changes * remove cvvp * style fix black * added tortoise config and updated config and args, refactoring the code * added tortoise to api * Pull mel_norm from url * Use TTS cleaners * Let download model files * add ability to pass tortoise presets through coqui api * fix tests * fix style and tests * fix tts commandline for tortoise * Add config.json to tortoise * Use kwargs * Use regular model api for loading tortoise * Add load from dir to synthesizer * Fix Tortoise floats * Use model_dir when there are multiple urls * Use `synthesize` when exists * lint fixes and resolve preset bug * resolve a download bug and update model link * fix json * do tortoise inference from voice dir * fix * fix test * fix speaker id and remove assests * update inference_tests.yml * replace inference_test.yml * fix extra dir as None * fix tests * remove space * Reformat docstring * Add docs * Update docs * lint fixes --------- Co-authored-by: Eren Gölge <egolge@coqui.ai> Co-authored-by: Eren Gölge <erogol@hotmail.com>
3.3 KiB
3.3 KiB
In [ ]:
#@title # Setup
# Imports used through the rest of the notebook.
import torch
import torchaudio
import torch.nn as nn
import torch.nn.functional as F
import IPython
from TTS.tts.models.tortoise import TextToSpeech
from TTS.tts.layers.tortoise.audio_utils import load_audio, load_voice, load_voices
# This will download all the models used by Tortoise from the HuggingFace hub.
tts = TextToSpeech()In [ ]:
# This is the text that will be spoken.
text = "Joining two modalities results in a surprising increase in generalization! What would happen if we combined them all?" #@param {type:"string"}
#@markdown Show code for multiline text input
# Here's something for the poetically inclined.. (set text=)
"""
Then took the other, as just as fair,
And having perhaps the better claim,
Because it was grassy and wanted wear;
Though as for that the passing there
Had worn them really about the same,"""
# Pick a "preset mode" to determine quality. Options: {"ultra_fast", "fast" (default), "standard", "high_quality"}. See docs in api.py
preset = "fast" #@param ["ultra_fast", "fast", "standard", "high_quality"]In [ ]:
%ls ../TTS/tts/utils/assets/tortoise/voices/
import IPython
IPython.display.Audio(filename='../TTS/tts/utils/assets/tortoise/voices/lj/1.wav')In [ ]:
#@markdown Pick one of the voices from the output above
voice = 'lj' #@param {type:"string"}
#@markdown Load it and send it through Tortoise.
voice_samples, conditioning_latents = load_voice(voice)
gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents,
preset=preset)
torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)
IPython.display.Audio('generated.wav')In [ ]: