Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ metrics:
|
|
19 |
|
20 |
# Text-to-Speech (TTS) with Tacotron2 trained on LJSpeech
|
21 |
|
22 |
-
This repository provides all the necessary tools for Text-to-Speech (TTS) with SpeechBrain using a [Tacotron2](https://arxiv.org/abs/1712.05884) pretrained on [
|
23 |
|
24 |
The pre-trained model takes in input a short text and produces a spectrogram in output. One can get the final waveform by applying a vocoder (e.g., HiFIGAN) on top of the generated spectrogram.
|
25 |
|
@@ -30,7 +30,7 @@ The pre-trained model takes in input a short text and produces a spectrogram in
|
|
30 |
pip install speechbrain
|
31 |
```
|
32 |
|
33 |
-
Please notice that we encourage you to read
|
34 |
[SpeechBrain](https://speechbrain.github.io).
|
35 |
|
36 |
### Perform Text-to-Speech (TTS)
|
@@ -41,7 +41,7 @@ from speechbrain.pretrained import Tacotron2
|
|
41 |
from speechbrain.pretrained import HIFIGAN
|
42 |
|
43 |
# Intialize TTS (tacotron2) and Vocoder (HiFIGAN)
|
44 |
-
tacotron2 = Tacotron2.from_hparams(source="
|
45 |
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder")
|
46 |
|
47 |
# Running the TTS
|
@@ -58,11 +58,10 @@ If you want to generate multiple sentences in one-shot, you can do in this way:
|
|
58 |
|
59 |
```
|
60 |
from speechbrain.pretrained import Tacotron2
|
61 |
-
tacotron2 = Tacotron2.from_hparams(source="
|
62 |
items = [
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"Never odd or even"
|
66 |
]
|
67 |
mel_outputs, mel_lengths, alignments = tacotron2.encode_batch(items)
|
68 |
|
|
|
19 |
|
20 |
# Text-to-Speech (TTS) with Tacotron2 trained on LJSpeech
|
21 |
|
22 |
+
This repository provides all the necessary tools for Text-to-Speech (TTS) with SpeechBrain using a [Tacotron2](https://arxiv.org/abs/1712.05884) pretrained on [ALLFA Public](https://github.com/getalp/ALFFA_PUBLIC/tree/master/ASR/SWAHILI).
|
23 |
|
24 |
The pre-trained model takes in input a short text and produces a spectrogram in output. One can get the final waveform by applying a vocoder (e.g., HiFIGAN) on top of the generated spectrogram.
|
25 |
|
|
|
30 |
pip install speechbrain
|
31 |
```
|
32 |
|
33 |
+
Please notice that we encourage you to read the tutorials and learn more about
|
34 |
[SpeechBrain](https://speechbrain.github.io).
|
35 |
|
36 |
### Perform Text-to-Speech (TTS)
|
|
|
41 |
from speechbrain.pretrained import HIFIGAN
|
42 |
|
43 |
# Intialize TTS (tacotron2) and Vocoder (HiFIGAN)
|
44 |
+
tacotron2 = Tacotron2.from_hparams(source="aioxlabs/tacotron-swahili", savedir="tmpdir_tts")
|
45 |
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder")
|
46 |
|
47 |
# Running the TTS
|
|
|
58 |
|
59 |
```
|
60 |
from speechbrain.pretrained import Tacotron2
|
61 |
+
tacotron2 = Tacotron2.from_hparams(source="aioxlabs/tacotron-swahili", savedir="tmpdir")
|
62 |
items = [
|
63 |
+
"raisi wa jumhuri ya tanzania",
|
64 |
+
"soma zaidi"
|
|
|
65 |
]
|
66 |
mel_outputs, mel_lengths, alignments = tacotron2.encode_batch(items)
|
67 |
|