Update README.md
Browse files
README.md
CHANGED
|
@@ -34,14 +34,14 @@ datasets:
|
|
| 34 |
It is the second released model from the [Parler-TTS](https://github.com/huggingface/parler-tts) project, which aims to provide the community with TTS training resources and dataset pre-processing code.
|
| 35 |
|
| 36 |
## 📖 Quick Index
|
| 37 |
-
* [Installation](#installation)
|
| 38 |
-
* [Using a random voice](#random-voice)
|
| 39 |
-
* [Using a specific speaker](#using-a-specific-speaker)
|
| 40 |
* [Motivation](#motivation)
|
| 41 |
|
| 42 |
-
## Usage
|
| 43 |
|
| 44 |
-
### Installation
|
| 45 |
|
| 46 |
Using Parler-TTS is as simple as "bonjour". Simply install the library once:
|
| 47 |
|
|
@@ -49,7 +49,7 @@ Using Parler-TTS is as simple as "bonjour". Simply install the library once:
|
|
| 49 |
pip install git+https://github.com/huggingface/parler-tts.git
|
| 50 |
```
|
| 51 |
|
| 52 |
-
### Random voice
|
| 53 |
|
| 54 |
|
| 55 |
**Parler-TTS** has been trained to generate speech with features that can be controlled with a simple text prompt, for example:
|
|
@@ -82,7 +82,7 @@ sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
|
|
| 82 |
* Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech
|
| 83 |
* The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt
|
| 84 |
|
| 85 |
-
### Using a specific speaker
|
| 86 |
|
| 87 |
To ensure speaker consistency across generations, this checkpoint was also trained on 34 speakers, characterized by name (e.g. Jon, Lea, Gary, Jenna, Mike, Laura).
|
| 88 |
|
|
|
|
| 34 |
It is the second released model from the [Parler-TTS](https://github.com/huggingface/parler-tts) project, which aims to provide the community with TTS training resources and dataset pre-processing code.
|
| 35 |
|
| 36 |
## 📖 Quick Index
|
| 37 |
+
* [👨💻 Installation](#installation)
|
| 38 |
+
* [🎲 Using a random voice](#random-voice)
|
| 39 |
+
* [🎯 Using a specific speaker](#using-a-specific-speaker)
|
| 40 |
* [Motivation](#motivation)
|
| 41 |
|
| 42 |
+
## 🛠️ Usage
|
| 43 |
|
| 44 |
+
### 👨💻 Installation
|
| 45 |
|
| 46 |
Using Parler-TTS is as simple as "bonjour". Simply install the library once:
|
| 47 |
|
|
|
|
| 49 |
pip install git+https://github.com/huggingface/parler-tts.git
|
| 50 |
```
|
| 51 |
|
| 52 |
+
### 🎲 Random voice
|
| 53 |
|
| 54 |
|
| 55 |
**Parler-TTS** has been trained to generate speech with features that can be controlled with a simple text prompt, for example:
|
|
|
|
| 82 |
* Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech
|
| 83 |
* The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt
|
| 84 |
|
| 85 |
+
### 🎯 Using a specific speaker
|
| 86 |
|
| 87 |
To ensure speaker consistency across generations, this checkpoint was also trained on 34 speakers, characterized by name (e.g. Jon, Lea, Gary, Jenna, Mike, Laura).
|
| 88 |
|