Hugging Face's logo

Spaces:
cocktailpeanut
/
maskgct
Running

App Files Community
maskgct
File size: 6,615 Bytes 
8c92a11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

######## Build Experiment Environment ###########
exp_dir=$(cd `dirname $0`; pwd)
work_dir=$(dirname $(dirname $(dirname $exp_dir)))

export WORK_DIR=$work_dir
export PYTHONPATH=$work_dir
export PYTHONIOENCODING=UTF-8

cd $work_dir/modules/monotonic_align
mkdir -p monotonic_align
python setup.py build_ext --inplace
cd $work_dir

######## Parse the Given Parameters from the Commond ###########
# options=$(getopt -o c:n:s --long gpu:,config:,infer_expt_dir:,infer_output_dir:,infer_source_file:,infer_source_audio_dir:,infer_target_speaker:,infer_key_shift:,infer_vocoder_dir:,name:,stage: -- "$@")
options=$(getopt -o c:n:s --long gpu:,config:,resume:,resume_from_ckpt_path:,resume_type:,infer_expt_dir:,infer_output_dir:,infer_mode:,infer_dataset:,infer_testing_set:,infer_text:,infer_speaker_name:,name:,stage: -- "$@")
eval set -- "$options"

while true; do
  case $1 in
    # Experimental Configuration File
    -c | --config) shift; exp_config=$1 ; shift ;;
    # Experimental Name
    -n | --name) shift; exp_name=$1 ; shift ;;
    # Running Stage
    -s | --stage) shift; running_stage=$1 ; shift ;;
    # Visible GPU machines. The default value is "0".
    --gpu) shift; gpu=$1 ; shift ;;

    # [Only for Training] Resume configuration
    --resume) shift; resume=$1 ; shift ;;
    # [Only for Training] The specific checkpoint path that you want to resume from.
    --resume_from_ckpt_path) shift; resume_from_ckpt_path=$1 ; shift ;;
    # [Only for Training] `resume` for loading all the things (including model weights, optimizer, scheduler, and random states). `finetune` for loading only the model weights.
    --resume_type) shift; resume_type=$1 ; shift ;;

    # [Only for Inference] The experiment dir. The value is like "[Your path to save logs and checkpoints]/[YourExptName]"
    --infer_expt_dir) shift; infer_expt_dir=$1 ; shift ;;
    # [Only for Inference] The output dir to save inferred audios. Its default value is "$expt_dir/result"
    --infer_output_dir) shift; infer_output_dir=$1 ; shift ;;
    # [Only for Inference] The inference mode. It can be "batch" to generate speech by batch, or "single" to generate a single clip of speech.
    --infer_mode) shift; infer_mode=$1 ; shift ;;
    # [Only for Inference] The inference dataset. It is only used when the inference mode is "batch".
    --infer_dataset) shift; infer_dataset=$1 ; shift ;;
    # [Only for Inference] The inference testing set. It is only used when the inference mode is "batch". It can be "test" set split from the dataset, or "golden_test" carefully selected from the testing set.
    --infer_testing_set) shift; infer_testing_set=$1 ; shift ;;
    # [Only for Inference] The text to be synthesized from. It is only used when the inference mode is "single". 
    --infer_text) shift; infer_text=$1 ; shift ;;
    # [Only for Inference] The chosen speaker's voice to be synthesized. It is only used when the inference mode is "single" for multi-speaker VITS.
    --infer_speaker_name) shift; infer_speaker_name=$1 ; shift ;;

    --) shift ; break ;;
    *) echo "Invalid option: $1" exit 1 ;;
  esac
done


### Value check ###
if [ -z "$running_stage" ]; then
    echo "[Error] Please specify the running stage"
    exit 1
fi

if [ -z "$exp_config" ]; then
    exp_config="${exp_dir}"/exp_config.json
fi
echo "Experimental Configuration File: $exp_config"

if [ -z "$gpu" ]; then
    gpu="0"
fi

######## Features Extraction ###########
if [ $running_stage -eq 1 ]; then
    CUDA_VISIBLE_DEVICES=$gpu python "${work_dir}"/bins/tts/preprocess.py \
        --config=$exp_config \
        --num_workers=4
fi

######## Training ###########
if [ $running_stage -eq 2 ]; then
    if [ -z "$exp_name" ]; then
        echo "[Error] Please specify the experiments name"
        exit 1
    fi
    echo "Experimental Name: $exp_name"

    # add default value
    if [ -z "$resume_from_ckpt_path" ]; then
        resume_from_ckpt_path=""
    fi

    if [ -z "$resume_type" ]; then
        resume_type="resume"
    fi

    if [ "$resume" = true ]; then
        echo "Resume from the existing experiment..."
        CUDA_VISIBLE_DEVICES="$gpu" accelerate launch "${work_dir}"/bins/tts/train.py \
            --config "$exp_config" \
            --exp_name "$exp_name" \
            --log_level info \
            --resume \
            --checkpoint_path "$resume_from_ckpt_path" \
            --resume_type "$resume_type"
    else
        echo "Start a new experiment..."
        CUDA_VISIBLE_DEVICES=$gpu accelerate launch "${work_dir}"/bins/tts/train.py \
            --config $exp_config \
            --exp_name $exp_name \
            --log_level debug
    fi
fi

######## Inference ###########
if [ $running_stage -eq 3 ]; then
    if [ -z "$infer_expt_dir" ]; then
        echo "[Error] Please specify the experimental directionary. The value is like [Your path to save logs and checkpoints]/[YourExptName]"
        exit 1
    fi

    if [ -z "$infer_output_dir" ]; then
        infer_output_dir="$expt_dir/result"
    fi

    if [ -z "$infer_mode" ]; then
        echo "[Error] Please specify the inference mode, e.g., "batch", "single""
        exit 1
    fi

    if [ "$infer_mode" = "batch" ] && [ -z "$infer_dataset" ]; then
        echo "[Error] Please specify the dataset used in inference when the inference mode is batch"
        exit 1
    fi

    if [ "$infer_mode" = "batch" ] && [ -z "$infer_testing_set" ]; then
        echo "[Error] Please specify the testing set used in inference when the inference mode is batch"
        exit 1
    fi
 
    if [ "$infer_mode" = "single" ] && [ -z "$infer_text" ]; then
        echo "[Error] Please specify the text to be synthesized when the inference mode is single"
        exit 1
    fi

    if [ "$infer_mode" = "single" ]; then
        echo 'Text: ' ${infer_text}
        infer_dataset=None
        infer_testing_set=None
    elif [ "$infer_mode" = "batch" ]; then
        infer_text=''
    fi
    
    if [ -z "$infer_speaker_name" ]; then
        infer_speaker_name=None
    fi

    


    CUDA_VISIBLE_DEVICES=$gpu accelerate launch "$work_dir"/bins/tts/inference.py \
        --config $exp_config \
        --acoustics_dir $infer_expt_dir \
        --output_dir $infer_output_dir  \
        --mode $infer_mode \
        --dataset $infer_dataset \
        --testing_set $infer_testing_set \
        --text "$infer_text" \
        --speaker_name $infer_speaker_name \
        --log_level debug



fi