mirror of
https://github.com/SWivid/F5-TTS.git
synced 2026-01-10 12:14:56 -08:00
266 lines
8.7 KiB
Python
266 lines
8.7 KiB
Python
import os
|
|
import re
|
|
import torch
|
|
import torchaudio
|
|
import gradio as gr
|
|
import numpy as np
|
|
import tempfile
|
|
from einops import rearrange
|
|
from ema_pytorch import EMA
|
|
from vocos import Vocos
|
|
from pydub import AudioSegment
|
|
from model import CFM, UNetT, DiT, MMDiT
|
|
from cached_path import cached_path
|
|
from model.utils import (
|
|
get_tokenizer,
|
|
convert_char_to_pinyin,
|
|
save_spectrogram,
|
|
)
|
|
from transformers import pipeline
|
|
import librosa
|
|
import click
|
|
|
|
device = (
|
|
"cuda"
|
|
if torch.cuda.is_available()
|
|
else "mps" if torch.backends.mps.is_available() else "cpu"
|
|
)
|
|
|
|
print(f"Using {device} device")
|
|
|
|
pipe = pipeline(
|
|
"automatic-speech-recognition",
|
|
model="openai/whisper-large-v3-turbo",
|
|
torch_dtype=torch.float16,
|
|
device=device,
|
|
)
|
|
|
|
# --------------------- Settings -------------------- #
|
|
|
|
target_sample_rate = 24000
|
|
n_mel_channels = 100
|
|
hop_length = 256
|
|
target_rms = 0.1
|
|
nfe_step = 32 # 16, 32
|
|
cfg_strength = 2.0
|
|
ode_method = "euler"
|
|
sway_sampling_coef = -1.0
|
|
speed = 1.0
|
|
# fix_duration = 27 # None or float (duration in seconds)
|
|
fix_duration = None
|
|
|
|
|
|
def load_model(exp_name, model_cls, model_cfg, ckpt_step):
|
|
checkpoint = torch.load(
|
|
str(cached_path(f"hf://SWivid/F5-TTS/{exp_name}/model_{ckpt_step}.pt")),
|
|
map_location=device,
|
|
)
|
|
vocab_char_map, vocab_size = get_tokenizer("Emilia_ZH_EN", "pinyin")
|
|
model = CFM(
|
|
transformer=model_cls(
|
|
**model_cfg, text_num_embeds=vocab_size, mel_dim=n_mel_channels
|
|
),
|
|
mel_spec_kwargs=dict(
|
|
target_sample_rate=target_sample_rate,
|
|
n_mel_channels=n_mel_channels,
|
|
hop_length=hop_length,
|
|
),
|
|
odeint_kwargs=dict(
|
|
method=ode_method,
|
|
),
|
|
vocab_char_map=vocab_char_map,
|
|
).to(device)
|
|
|
|
ema_model = EMA(model, include_online_model=False).to(device)
|
|
ema_model.load_state_dict(checkpoint["ema_model_state_dict"])
|
|
ema_model.copy_params_from_ema_to_model()
|
|
|
|
return ema_model, model
|
|
|
|
|
|
# load models
|
|
F5TTS_model_cfg = dict(
|
|
dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4
|
|
)
|
|
E2TTS_model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
|
|
|
|
F5TTS_ema_model, F5TTS_base_model = load_model(
|
|
"F5TTS_Base", DiT, F5TTS_model_cfg, 1200000
|
|
)
|
|
E2TTS_ema_model, E2TTS_base_model = load_model(
|
|
"E2TTS_Base", UNetT, E2TTS_model_cfg, 1200000
|
|
)
|
|
|
|
|
|
def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence):
|
|
print(gen_text)
|
|
if len(gen_text) > 200:
|
|
raise gr.Error("Please keep your text under 200 chars.")
|
|
gr.Info("Converting audio...")
|
|
with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as f:
|
|
aseg = AudioSegment.from_file(ref_audio_orig)
|
|
audio_duration = len(aseg)
|
|
if audio_duration > 15000:
|
|
gr.Warning("Audio is over 15s, clipping to only first 15s.")
|
|
aseg = aseg[:15000]
|
|
aseg.export(f.name, format="wav")
|
|
ref_audio = f.name
|
|
if exp_name == "F5-TTS":
|
|
ema_model = F5TTS_ema_model
|
|
base_model = F5TTS_base_model
|
|
elif exp_name == "E2-TTS":
|
|
ema_model = E2TTS_ema_model
|
|
base_model = E2TTS_base_model
|
|
|
|
if not ref_text.strip():
|
|
gr.Info("No reference text provided, transcribing reference audio...")
|
|
ref_text = outputs = pipe(
|
|
ref_audio,
|
|
chunk_length_s=30,
|
|
batch_size=128,
|
|
generate_kwargs={"task": "transcribe"},
|
|
return_timestamps=False,
|
|
)["text"].strip()
|
|
gr.Info("Finished transcription")
|
|
else:
|
|
gr.Info("Using custom reference text...")
|
|
audio, sr = torchaudio.load(ref_audio)
|
|
|
|
rms = torch.sqrt(torch.mean(torch.square(audio)))
|
|
if rms < target_rms:
|
|
audio = audio * target_rms / rms
|
|
if sr != target_sample_rate:
|
|
resampler = torchaudio.transforms.Resample(sr, target_sample_rate)
|
|
audio = resampler(audio)
|
|
audio = audio.to(device)
|
|
|
|
# Prepare the text
|
|
text_list = [ref_text + gen_text]
|
|
final_text_list = convert_char_to_pinyin(text_list)
|
|
|
|
# Calculate duration
|
|
ref_audio_len = audio.shape[-1] // hop_length
|
|
# if fix_duration is not None:
|
|
# duration = int(fix_duration * target_sample_rate / hop_length)
|
|
# else:
|
|
zh_pause_punc = r"。，、；：？！"
|
|
ref_text_len = len(ref_text) + len(re.findall(zh_pause_punc, ref_text))
|
|
gen_text_len = len(gen_text) + len(re.findall(zh_pause_punc, gen_text))
|
|
duration = ref_audio_len + int(ref_audio_len / ref_text_len * gen_text_len / speed)
|
|
|
|
# inference
|
|
gr.Info(f"Generating audio using {exp_name}")
|
|
with torch.inference_mode():
|
|
generated, _ = base_model.sample(
|
|
cond=audio,
|
|
text=final_text_list,
|
|
duration=duration,
|
|
steps=nfe_step,
|
|
cfg_strength=cfg_strength,
|
|
sway_sampling_coef=sway_sampling_coef,
|
|
)
|
|
|
|
generated = generated[:, ref_audio_len:, :]
|
|
generated_mel_spec = rearrange(generated, "1 n d -> 1 d n")
|
|
gr.Info("Running vocoder")
|
|
vocos = Vocos.from_pretrained("charactr/vocos-mel-24khz")
|
|
generated_wave = vocos.decode(generated_mel_spec.cpu())
|
|
if rms < target_rms:
|
|
generated_wave = generated_wave * rms / target_rms
|
|
|
|
# wav -> numpy
|
|
generated_wave = generated_wave.squeeze().cpu().numpy()
|
|
|
|
if remove_silence:
|
|
gr.Info("Removing audio silences... This may take a moment")
|
|
non_silent_intervals = librosa.effects.split(generated_wave, top_db=30)
|
|
non_silent_wave = np.array([])
|
|
for interval in non_silent_intervals:
|
|
start, end = interval
|
|
non_silent_wave = np.concatenate(
|
|
[non_silent_wave, generated_wave[start:end]]
|
|
)
|
|
generated_wave = non_silent_wave
|
|
|
|
# spectogram
|
|
with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp_spectrogram:
|
|
spectrogram_path = tmp_spectrogram.name
|
|
save_spectrogram(generated_mel_spec[0].cpu().numpy(), spectrogram_path)
|
|
|
|
return (target_sample_rate, generated_wave), spectrogram_path
|
|
|
|
|
|
with gr.Blocks() as app:
|
|
gr.Markdown(
|
|
"""
|
|
# E2/F5 TTS
|
|
|
|
This is a local web UI for F5 TTS, based on the unofficial [online demo](https://huggingface.co/spaces/mrfakename/E2-F5-TTS). This app supports the following TTS models:
|
|
|
|
* [F5-TTS](https://arxiv.org/abs/2410.06885) (A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching)
|
|
* [E2-TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS)
|
|
|
|
The checkpoints support English and Chinese.
|
|
|
|
If you're having issues, try converting your reference audio to WAV or MP3, clipping it to 15s, and shortening your prompt.
|
|
|
|
**NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.**
|
|
"""
|
|
)
|
|
|
|
ref_audio_input = gr.Audio(label="Reference Audio", type="filepath")
|
|
gen_text_input = gr.Textbox(label="Text to Generate (max 200 chars.)", lines=4)
|
|
model_choice = gr.Radio(
|
|
choices=["F5-TTS", "E2-TTS"], label="Choose TTS Model", value="F5-TTS"
|
|
)
|
|
generate_btn = gr.Button("Synthesize", variant="primary")
|
|
with gr.Accordion("Advanced Settings", open=False):
|
|
ref_text_input = gr.Textbox(
|
|
label="Reference Text",
|
|
info="Leave blank to automatically transcribe the reference audio. If you enter text it will override automatic transcription.",
|
|
lines=2,
|
|
)
|
|
remove_silence = gr.Checkbox(
|
|
label="Remove Silences",
|
|
info="The model tends to produce silences, especially on longer audio. We can manually remove silences if needed. Note that this is an experimental feature and may produce strange results. This will also increase generation time.",
|
|
value=True,
|
|
)
|
|
|
|
audio_output = gr.Audio(label="Synthesized Audio")
|
|
spectrogram_output = gr.Image(label="Spectrogram")
|
|
|
|
generate_btn.click(
|
|
infer,
|
|
inputs=[
|
|
ref_audio_input,
|
|
ref_text_input,
|
|
gen_text_input,
|
|
model_choice,
|
|
remove_silence,
|
|
],
|
|
outputs=[audio_output, spectrogram_output],
|
|
)
|
|
|
|
|
|
@click.command()
|
|
@click.option("--port", "-p", default=None, help="Port to run the app on")
|
|
@click.option("--host", "-H", default=None, help="Host to run the app on")
|
|
@click.option(
|
|
"--share",
|
|
"-s",
|
|
default=False,
|
|
is_flag=True,
|
|
help="Share the app via Gradio share link",
|
|
)
|
|
@click.option("--api", "-a", default=True, is_flag=True, help="Allow API access")
|
|
def main(port, host, share, api):
|
|
global app
|
|
print(f"Starting app...")
|
|
app.queue(api_open=api).launch(
|
|
server_name=host, server_port=port, share=share, show_api=api
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|