File size: 8,475 Bytes
f25cff8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
import argparse
import codecs
import os
import re
from importlib.resources import files
from pathlib import Path

import numpy as np
import soundfile as sf
import tomli
from cached_path import cached_path
import pandas as pd

from f5_tts.infer.utils_infer import (
    infer_process,
    load_model,
    load_vocoder,
    preprocess_ref_audio_text,
    remove_silence_for_generated_wav,
)
from f5_tts.model import DiT, UNetT

parser = argparse.ArgumentParser(
    prog="python3 infer-cli.py",
    description="Commandline interface for E2/F5 TTS with Advanced Batch Processing.",
    epilog="Specify options above to override one or more settings from config.",
)
parser.add_argument(
    "-c",
    "--config",
    help="Configuration file. Default=infer/examples/basic/basic.toml",
    default=os.path.join(files("f5_tts").joinpath("infer/examples/basic"), "basic.toml"),
)
parser.add_argument(
    "-m",
    "--model",
    help="F5-TTS | E2-TTS",
)
parser.add_argument(
    "-p",
    "--ckpt_file",
    help="The Checkpoint .pt",
)
parser.add_argument(
    "-v",
    "--vocab_file",
    help="The vocab .txt",
)
parser.add_argument("-r", "--ref_audio", type=str, help="Reference audio file < 15 seconds.")
parser.add_argument("-s", "--ref_text", type=str, default="666", help="Subtitle for the reference audio.")
parser.add_argument(
    "-t",
    "--gen_text",
    type=str,
    help="Text to generate.",
)
parser.add_argument(
    "-f",
    "--gen_file",
    type=str,
    help="File with text to generate. Ignores --gen_text",
)
parser.add_argument(
    "-o",
    "--output_dir",
    type=str,
    help="Path to output folder..",
)
parser.add_argument(
    "-w",
    "--output_file",
    type=str,
    help="Filename of output file..",
)
parser.add_argument(
    "--remove_silence",
    help="Remove silence.",
)
parser.add_argument("--vocoder_name", type=str, default="vocos", choices=["vocos", "bigvgan"], help="vocoder name")
parser.add_argument(
    "--load_vocoder_from_local",
    action="store_true",
    help="load vocoder from local. Default: ../checkpoints/charactr/vocos-mel-24khz",
)
parser.add_argument(
    "--speed",
    type=float,
    default=1.0,
    help="Adjust the speed of the audio generation (default: 1.0)",
)
args = parser.parse_args()

config = tomli.load(open(args.config, "rb"))

ref_audio = args.ref_audio if args.ref_audio else config["ref_audio"]
ref_text = args.ref_text if args.ref_text != "666" else config["ref_text"]
gen_file = args.gen_file if args.gen_file else config["gen_file"]


if gen_file:
    # Read texts from CSV file
    df = pd.read_csv(gen_file)
    text_list = df['text'].tolist()
else:
    # If no file provided, use single text
    gen_text = args.gen_text if args.gen_text else config["gen_text"]
    text_list = [gen_text]
output_dir = args.output_dir if args.output_dir else config["output_dir"]
output_file = args.output_file if args.output_file else config["output_file"]
model = args.model if args.model else config["model"]
ckpt_file = args.ckpt_file if args.ckpt_file else ""
vocab_file = args.vocab_file if args.vocab_file else ""
remove_silence = args.remove_silence if args.remove_silence else config["remove_silence"]
speed = args.speed

wave_path = Path(output_dir) / output_file
# spectrogram_path = Path(output_dir) / "infer_cli_out.png"


# patches for pip pkg user
if "infer/examples/" in ref_audio:
    ref_audio = str(files("f5_tts").joinpath(f"{ref_audio}"))
if "infer/examples/" in gen_file:
    gen_file = str(files("f5_tts").joinpath(f"{gen_file}"))
if "voices" in config:
    for voice in config["voices"]:
        voice_ref_audio = config["voices"][voice]["ref_audio"]
        if "infer/examples/" in voice_ref_audio:
            config["voices"][voice]["ref_audio"] = str(files("f5_tts").joinpath(f"{voice_ref_audio}"))

vocoder_name = args.vocoder_name
mel_spec_type = args.vocoder_name
if vocoder_name == "vocos":
    vocoder_local_path = "../checkpoints/vocos-mel-24khz"
elif vocoder_name == "bigvgan":
    vocoder_local_path = "../checkpoints/bigvgan_v2_24khz_100band_256x"

vocoder = load_vocoder(vocoder_name=mel_spec_type, is_local=args.load_vocoder_from_local, local_path=vocoder_local_path)


# load models
if model == "F5-TTS":
    model_cls = DiT
    model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)
    if ckpt_file == "":
        if vocoder_name == "vocos":
            repo_name = "F5-TTS"
            exp_name = "F5TTS_Base"
            ckpt_step = 1200000
            ckpt_file = str(cached_path(f"hf://SWivid/{repo_name}/{exp_name}/model_{ckpt_step}.safetensors"))
            # ckpt_file = f"ckpts/{exp_name}/model_{ckpt_step}.pt"  # .pt | .safetensors; local path
        elif vocoder_name == "bigvgan":
            repo_name = "F5-TTS"
            exp_name = "F5TTS_Base_bigvgan"
            ckpt_step = 1250000
            ckpt_file = str(cached_path(f"hf://SWivid/{repo_name}/{exp_name}/model_{ckpt_step}.pt"))

elif model == "E2-TTS":
    assert vocoder_name == "vocos", "E2-TTS only supports vocoder vocos"
    model_cls = UNetT
    model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
    if ckpt_file == "":
        repo_name = "E2-TTS"
        exp_name = "E2TTS_Base"
        ckpt_step = 1200000
        ckpt_file = str(cached_path(f"hf://SWivid/{repo_name}/{exp_name}/model_{ckpt_step}.safetensors"))
        # ckpt_file = f"ckpts/{exp_name}/model_{ckpt_step}.pt"  # .pt | .safetensors; local path


print(f"Using {model}...")
ema_model = load_model(model_cls, model_cfg, ckpt_file, mel_spec_type=mel_spec_type, vocab_file=vocab_file)


def main_process(ref_audio, ref_text, text_list, model_obj, mel_spec_type, remove_silence, speed):
    main_voice = {"ref_audio": ref_audio, "ref_text": ref_text}
    if "voices" not in config:
        voices = {"main": main_voice}
    else:
        voices = config["voices"]
        voices["main"] = main_voice
    for voice in voices:
        voices[voice]["ref_audio"], voices[voice]["ref_text"] = preprocess_ref_audio_text(
            voices[voice]["ref_audio"], voices[voice]["ref_text"]
        )
        print("Voice:", voice)
        print("Ref_audio:", voices[voice]["ref_audio"])
        print("Ref_text:", voices[voice]["ref_text"])

    # Process each text in the list
    for idx, text_gen in enumerate(text_list):
        generated_audio_segments = []
        reg1 = r"(?=\[\w+\])"
        chunks = re.split(reg1, text_gen)
        reg2 = r"\[(\w+)\]"
        for text in chunks:
            if not text.strip():
                continue
            match = re.match(reg2, text)
            if match:
                voice = match[1]
            else:
                print("No voice tag found, using main.")
                voice = "main"
            if voice not in voices:
                print(f"Voice {voice} not found, using main.")
                voice = "main"
            text = re.sub(reg2, "", text)
            gen_text = text.strip()
            ref_audio = voices[voice]["ref_audio"]
            ref_text = voices[voice]["ref_text"]
            print(f"Voice: {voice}")
            audio, final_sample_rate, spectragram = infer_process(
                ref_audio, ref_text, gen_text, model_obj, vocoder, mel_spec_type=mel_spec_type, speed=speed
            )
            generated_audio_segments.append(audio)

        if generated_audio_segments:
            final_wave = np.concatenate(generated_audio_segments)

            if not os.path.exists(output_dir):
                os.makedirs(output_dir)

            # Get first 3 words from the text
            first_three_words = '_'.join(text_gen.split()[:3])
            # Remove any special characters that might cause issues in filenames
            first_three_words = re.sub(r'[^\w\s-]', '', first_three_words)
            # Create filename with index and first 3 words
            filename = f"{Path(output_file).stem}__sentence{(idx+1):03d}_{first_three_words}{Path(output_file).suffix}"

            wave_path = Path(output_dir) / filename

            with open(wave_path, "wb") as f:
                sf.write(f.name, final_wave, final_sample_rate)
                # Remove silence
                if remove_silence:
                    remove_silence_for_generated_wav(f.name)
                print(f"Generated audio saved to: {f.name}")


def main():
    main_process(ref_audio, ref_text, text_list, ema_model, mel_spec_type, remove_silence, speed)


if __name__ == "__main__":
    main()