Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- text-to-speech
|
5 |
+
- annotation
|
6 |
+
license: apache-2.0
|
7 |
+
language:
|
8 |
+
- en
|
9 |
+
- as
|
10 |
+
- bn
|
11 |
+
- gu
|
12 |
+
- hi
|
13 |
+
- kn
|
14 |
+
- ks
|
15 |
+
- or
|
16 |
+
- ml
|
17 |
+
- mr
|
18 |
+
- ne
|
19 |
+
- pa
|
20 |
+
- sa
|
21 |
+
- sd
|
22 |
+
- ta
|
23 |
+
- te
|
24 |
+
- ur
|
25 |
+
- om
|
26 |
+
pipeline_tag: text-to-speech
|
27 |
+
inference: false
|
28 |
+
base_model:
|
29 |
+
- ai4bharat/indic-parler-tts
|
30 |
+
---
|
31 |
+
# HelpingAI-TTS-v1 🎤🔥
|
32 |
+
|
33 |
+
Yo, what's good! Welcome to **HelpingAI-TTS-v1**, your go-to for next-level Text-to-Speech (TTS) that's all about personalization, vibes, and clarity. Whether you want your text to sound cheerful, emotional, or just like you're chatting with a friend, this model's got you covered. 💯
|
34 |
+
|
35 |
+
|
36 |
+
## 🚀 What’s HelpingAI-TTS-v1?
|
37 |
+
|
38 |
+
**HelpingAI-TTS-v1** is a beast when it comes to generating **high-quality, customizable speech**. It doesn’t just spit out generic text; it **feels** what you're saying and brings it to life with style. Add a description to your speech, like how fast or slow it should be, if it’s cheerful or serious, and BOOM — you got yourself the perfect audio output. 🎧
|
39 |
+
|
40 |
+
|
41 |
+
## 🛠️ How It Works: A Quick Rundown 🔥
|
42 |
+
|
43 |
+
1. **Transcript**: The text you want to speak. Keep it casual, formal, or whatever suits your vibe.
|
44 |
+
2. **Caption**: Describes how you want the speech to sound. Want a fast-paced, hype vibe or a calm, soothing tone? Just say it. 🔥
|
45 |
+
|
46 |
+
|
47 |
+
## 💡 Features You’ll Love:
|
48 |
+
|
49 |
+
- **Expressive Speech**: This isn’t just any TTS. You can describe the tone, speed, and vibe you want. Whether it's a *peppy* "Hey!" or a *chill* "What's up?", this model’s got your back.
|
50 |
+
- **Top-Notch Quality**: Super clean audio. No static. Just pure, high-quality sound that makes your words pop.
|
51 |
+
- **Customizable Like Never Before**: Play with emotions, tone, and even accents. It’s all about making it personal. 🌍
|
52 |
+
|
53 |
+
## 🔧 Get Started: Installation 🔥
|
54 |
+
|
55 |
+
Ready to vibe? Here’s how you set up **HelpingAI-TTS-v1** in seconds:
|
56 |
+
|
57 |
+
```bash
|
58 |
+
pip install git+https://github.com/huggingface/parler-tts.git
|
59 |
+
```
|
60 |
+
|
61 |
+
|
62 |
+
## 🖥️ Usage: Let's Make Some Magic 🎤
|
63 |
+
|
64 |
+
Here’s the code that gets the job done. Super simple to use, just plug in your text and describe how you want it to sound. It’s like setting the mood for a movie.
|
65 |
+
|
66 |
+
```python
|
67 |
+
import torch
|
68 |
+
from parler_tts import ParlerTTSForConditionalGeneration
|
69 |
+
from transformers import AutoTokenizer
|
70 |
+
import soundfile as sf
|
71 |
+
|
72 |
+
# Choose your device (GPU or CPU)
|
73 |
+
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
74 |
+
|
75 |
+
# Load the model and tokenizers
|
76 |
+
model = ParlerTTSForConditionalGeneration.from_pretrained("HelpingAI/HelpingAI-TTS-v1").to(device)
|
77 |
+
tokenizer = AutoTokenizer.from_pretrained("HelpingAI/HelpingAI-TTS-v1")
|
78 |
+
description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)
|
79 |
+
|
80 |
+
# Customize your inputs: text + description
|
81 |
+
prompt = "Hey, what's up? How’s it going?"
|
82 |
+
description = "A friendly, upbeat, and casual tone with a moderate speed. Speaker sounds confident and relaxed."
|
83 |
+
|
84 |
+
# Tokenize the inputs
|
85 |
+
input_ids = description_tokenizer(description, return_tensors="pt").input_ids.to(device)
|
86 |
+
prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
|
87 |
+
|
88 |
+
# Generate the audio
|
89 |
+
generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
|
90 |
+
audio_arr = generation.cpu().numpy().squeeze()
|
91 |
+
|
92 |
+
# Save the audio to a file
|
93 |
+
sf.write("output.wav", audio_arr, model.config.sampling_rate)
|
94 |
+
```
|
95 |
+
|
96 |
+
This will create a **super clean** `.wav` file with the speech you asked for. 🔥
|
97 |
+
|
98 |
+
|
99 |
+
## 🌍 Language Support: Speak Your Language
|
100 |
+
|
101 |
+
No matter where you're from, **HelpingAI-TTS-v1** has you covered. **Officially** supporting 20+ languages and **unofficial** support for a few more. That’s global vibes right there. 🌏
|
102 |
+
|
103 |
+
- Assamese
|
104 |
+
- Bengali
|
105 |
+
- Bodo
|
106 |
+
- Dogri
|
107 |
+
- Kannada
|
108 |
+
- Malayalam
|
109 |
+
- Marathi
|
110 |
+
- Sanskrit
|
111 |
+
- Nepali
|
112 |
+
- English
|
113 |
+
- Telugu
|
114 |
+
- Hindi
|
115 |
+
- Gujarati
|
116 |
+
- Konkani
|
117 |
+
- Maithili
|
118 |
+
- Manipuri
|
119 |
+
- Odia
|
120 |
+
- Santali
|
121 |
+
- Sindhi
|
122 |
+
- Tamil
|
123 |
+
- Urdu
|
124 |
+
- Chhattisgarhi
|
125 |
+
- Kashmiri
|
126 |
+
- Punjabi
|
127 |
+
|
128 |
+
|
129 |
+
*Powered by HelpingAI, where we blend emotional intelligence with tech.* 🌟
|