File size: 7,366 Bytes
dc780c5
837713d
 
a07119c
 
 
 
837713d
 
 
 
 
 
 
8b1a278
837713d
 
 
 
 
 
 
2b1d793
837713d
 
 
fa080ce
88dfd37
fa080ce
 
837713d
 
 
 
 
fa080ce
837713d
 
 
fa080ce
6adc644
837713d
 
 
a07119c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8d5a618
837713d
 
a07119c
837713d
 
 
 
 
 
 
dc780c5
837713d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc780c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b1a278
dc780c5
 
 
 
 
 
 
 
 
 
 
 
837713d
 
 
 
 
 
 
 
 
 
 
 
50a7cb9
 
 
 
8b0fa06
50a7cb9
 
0b86c09
88dfd37
 
837713d
 
a07119c
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
import spaces
import gradio as gr
import torch
from transformers.models.speecht5.number_normalizer import EnglishNumberNormalizer
from string import punctuation
import re


from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer, AutoFeatureExtractor, set_seed

device = "cuda:0" if torch.cuda.is_available() else "cpu"


repo_id = "parler-tts/parler_tts_mini_v0.1"

model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
tokenizer = AutoTokenizer.from_pretrained(repo_id)
feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)


SAMPLE_RATE = feature_extractor.sampling_rate
SEED = 42

default_text = "Please surprise me and speak in whatever voice you enjoy."
examples = [
    [
        "Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
        "A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone."
    ],
    [
        "'This is the best time of my life, Bartley,' she said happily.",
        "A female speaker with a slightly low-pitched, quite monotone voice delivers her words at a slightly faster-than-average pace in a confined space with very clear audio.",
    ],
    [
        "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
        "A male speaker with a slightly high-pitched voice delivering his words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
    ],
    [
        "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
        "A male speaker with a low-pitched voice delivers his words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
    ],
]

number_normalizer = EnglishNumberNormalizer()

def preprocess(text):
    text = number_normalizer(text).strip()
    text = text.replace("-", " ")
    if text[-1] not in punctuation:
        text = f"{text}."
    
    abbreviations_pattern = r'\b[A-Z][A-Z\.]+\b'
    
    def separate_abb(chunk):
        chunk = chunk.replace(".","")
        print(chunk)
        return " ".join(chunk)
    
    abbreviations = re.findall(abbreviations_pattern, text)
    for abv in abbreviations:
        if abv in text:
            text = text.replace(abv, separate_abb(abv))
    return text

@spaces.GPU
def gen_tts(text, description):
    inputs = tokenizer(description, return_tensors="pt").to(device)
    prompt = tokenizer(preprocess(text), return_tensors="pt").to(device)

    set_seed(SEED)
    generation = model.generate(
        input_ids=inputs.input_ids, prompt_input_ids=prompt.input_ids, do_sample=True, temperature=1.0
    )
    audio_arr = generation.cpu().numpy().squeeze()

    return SAMPLE_RATE, audio_arr


css = """
        #share-btn-container {
            display: flex;
            padding-left: 0.5rem !important;
            padding-right: 0.5rem !important;
            background-color: #000000;
            justify-content: center;
            align-items: center;
            border-radius: 9999px !important; 
            width: 13rem;
            margin-top: 10px;
            margin-left: auto;
            flex: unset !important;
        }
        #share-btn {
            all: initial;
            color: #ffffff;
            font-weight: 600;
            cursor: pointer;
            font-family: 'IBM Plex Sans', sans-serif;
            margin-left: 0.5rem !important;
            padding-top: 0.25rem !important;
            padding-bottom: 0.25rem !important;
            right:0;
        }
        #share-btn * {
            all: unset !important;
        }
        #share-btn-container div:nth-child(-n+2){
            width: auto !important;
            min-height: 0px !important;
        }
        #share-btn-container .wrap {
            display: none !important;
        }
"""
with gr.Blocks(css=css) as block:
    gr.HTML(
        """
            <div style="text-align: center; max-width: 700px; margin: 0 auto;">
              <div
                style="
                  display: inline-flex; align-items: center; gap: 0.8rem; font-size: 1.75rem;
                "
              >
                <h1 style="font-weight: 900; margin-bottom: 7px; line-height: normal;">
                  Parler-TTS 🗣️
                </h1>
              </div>
            </div>
        """
    )
    gr.HTML(
        f"""
        <p><a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a> is a training and inference library for
        high-fidelity text-to-speech (TTS) models. The model demonstrated here, <a href="https://huggingface.co/parler-tts/parler_tts_mini_v0.1"> Parler-TTS Mini v0.1</a>, 
        is the first iteration model trained using 10k hours of narrated audiobooks. It generates high-quality speech 
        with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).</p>

        <p>Tips for ensuring good generation:
        <ul>
            <li>Include the term "very clear audio" to generate the highest quality audio, and "very noisy audio" for high levels of background noise</li>
            <li>Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech</li>
            <li>The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt</li>
        </ul>
        </p>
        """
    )
    with gr.Row():
        with gr.Column():
            input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
            description = gr.Textbox(label="Description", lines=2, value="", elem_id="input_description")
            run_button = gr.Button("Generate Audio", variant="primary")
        with gr.Column():
            audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out")

    inputs = [input_text, description]
    outputs = [audio_out]
    gr.Examples(examples=examples, fn=gen_tts, inputs=inputs, outputs=outputs, cache_examples=True)
    run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)
    gr.HTML(
        """
        <p>To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data to 50k hours of speech.
        The v1 release of the model will be trained on this data, as well as inference optimisations, such as flash attention
        and torch compile, that will improve the latency by 2-4x. If you want to find out more about how this model was trained and even fine-tune it yourself, check-out the 
        <a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a> repository on GitHub.</p>
        
        <p>The Parler-TTS codebase and its associated checkpoints are licensed under <a href='https://github.com/huggingface/parler-tts?tab=Apache-2.0-1-ov-file#readme'> Apache 2.0</a>.</p>
        """
    )

block.queue()
block.launch(share=True)