Skip to content
This repository was archived by the owner on Feb 5, 2024. It is now read-only.

Commit 5dc347c

Browse files
authored
Add female voices (#4)
* add nancy voice * add ljspeech voice * docker instructions authored-by: jarbasai <jarbasai@mailfence.com>
1 parent c5e5473 commit 5dc347c

File tree

3 files changed

+40
-1
lines changed

3 files changed

+40
-1
lines changed

ljspeech.Dockerfile

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
FROM tensorflow/tensorflow:1.8.0-py3
2+
RUN apt-get update && apt-get install -y python3 python3-pip git llvm-8
3+
RUN ln -s /usr/bin/llvm-config-8 /usr/bin/llvm-config
4+
5+
RUN git clone https://github.com/keithito/tacotron /root/tacotron
6+
WORKDIR /root/tacotron
7+
RUN pip3 install -r requirements.txt
8+
9+
RUN mkdir /root/tacotron_models
10+
RUN curl https://data.keithito.com/data/speech/tacotron-20180906.tar.gz -k --output /root/tacotron_models/tacotron-20180906.tar.gz
11+
WORKDIR /root/tacotron_models
12+
RUN tar x --file /root/tacotron_models/tacotron-20180906.tar.gz
13+
WORKDIR /root/tacotron
14+
15+
CMD python3 /root/tacotron/demo_server.py --checkpoint /root/tacotron_models/tacotron-20180906/model.ckpt

nancy.Dockerfile

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
FROM tensorflow/tensorflow:1.8.0-py3
2+
RUN apt-get update && apt-get install -y python3 python3-pip git llvm-8
3+
RUN ln -s /usr/bin/llvm-config-8 /usr/bin/llvm-config
4+
5+
RUN git clone https://github.com/keithito/tacotron /root/tacotron
6+
WORKDIR /root/tacotron
7+
RUN git reset --hard 8edcd55b3f08f0492340e8b3ee60a693138f5473
8+
RUN pip3 install -r requirements.txt
9+
10+
RUN git clone https://github.com/ArkaneCow/tacotron-models /root/tacotron_models
11+
12+
CMD python3 /root/tacotron/demo_server.py --checkpoint /root/tacotron_models/mxgray_nancy/model.ckpt-250000

readme.md

Lines changed: 13 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,19 @@ OVOS TTS plugin for [Mimic2](https://github.com/MycroftAI/mimic2)
1010

1111
```json
1212
"tts": {
13-
"module": "ovos-tts-plugin-mimic2"
13+
"module": "ovos-tts-plugin-mimic2",
14+
"ovos-tts-plugin-mimic2": {
15+
"url": "https://mimic-api.mycroft.ai/synthesize"
16+
}
1417
}
1518

1619
```
20+
21+
### Voices
22+
23+
Dockerfiles are provided for Nancy corpus trained by Mxgray and LJSpeech trained by Keithito
24+
- `docker build -f nancy.Dockerfile -t mimic2-nancy`
25+
- `docker build -f ljspeech.Dockerfile -t mimic2-ljspeech`
26+
27+
run the container and set url in config `http://0.0.0.0:9000/synthesize`
28+
- `docker run --rm -p 9000:9000 mimic2-nancy`

0 commit comments

Comments
 (0)