mrfakename commited on
Commit
a576047
1 Parent(s): cf68f41

Sync from GitHub repo

Browse files

This Space is synced from the GitHub repo: https://github.com/SWivid/F5-TTS. Please submit contributions to the Space there

src/f5_tts/infer/examples/basic/basic.toml CHANGED
@@ -7,4 +7,5 @@ gen_text = "I don't really care what you call me. I've been a silent spectator,
7
  # File with text to generate. Ignores the text above.
8
  gen_file = ""
9
  remove_silence = false
10
- output_dir = "tests"
 
 
7
  # File with text to generate. Ignores the text above.
8
  gen_file = ""
9
  remove_silence = false
10
+ output_dir = "tests"
11
+ output_file = "infer_cli_out.wav"
src/f5_tts/infer/infer_cli.py CHANGED
@@ -57,7 +57,7 @@ parser.add_argument(
57
  "-f",
58
  "--gen_file",
59
  type=str,
60
- help="File with text to generate. Ignores --text",
61
  )
62
  parser.add_argument(
63
  "-o",
@@ -65,6 +65,12 @@ parser.add_argument(
65
  type=str,
66
  help="Path to output folder..",
67
  )
 
 
 
 
 
 
68
  parser.add_argument(
69
  "--remove_silence",
70
  help="Remove silence.",
@@ -104,13 +110,14 @@ if "voices" in config:
104
  if gen_file:
105
  gen_text = codecs.open(gen_file, "r", "utf-8").read()
106
  output_dir = args.output_dir if args.output_dir else config["output_dir"]
 
107
  model = args.model if args.model else config["model"]
108
  ckpt_file = args.ckpt_file if args.ckpt_file else ""
109
  vocab_file = args.vocab_file if args.vocab_file else ""
110
  remove_silence = args.remove_silence if args.remove_silence else config["remove_silence"]
111
  speed = args.speed
112
 
113
- wave_path = Path(output_dir) / "infer_cli_out.wav"
114
  # spectrogram_path = Path(output_dir) / "infer_cli_out.png"
115
 
116
  vocoder_name = args.vocoder_name
 
57
  "-f",
58
  "--gen_file",
59
  type=str,
60
+ help="File with text to generate. Ignores --gen_text",
61
  )
62
  parser.add_argument(
63
  "-o",
 
65
  type=str,
66
  help="Path to output folder..",
67
  )
68
+ parser.add_argument(
69
+ "-w",
70
+ "--output_file",
71
+ type=str,
72
+ help="Filename of output file..",
73
+ )
74
  parser.add_argument(
75
  "--remove_silence",
76
  help="Remove silence.",
 
110
  if gen_file:
111
  gen_text = codecs.open(gen_file, "r", "utf-8").read()
112
  output_dir = args.output_dir if args.output_dir else config["output_dir"]
113
+ output_file = args.output_file if args.output_file else config["output_file"]
114
  model = args.model if args.model else config["model"]
115
  ckpt_file = args.ckpt_file if args.ckpt_file else ""
116
  vocab_file = args.vocab_file if args.vocab_file else ""
117
  remove_silence = args.remove_silence if args.remove_silence else config["remove_silence"]
118
  speed = args.speed
119
 
120
+ wave_path = Path(output_dir) / output_file
121
  # spectrogram_path = Path(output_dir) / "infer_cli_out.png"
122
 
123
  vocoder_name = args.vocoder_name