ik commited on
Commit
e3109ec
·
1 Parent(s): 92c5aa5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -36
README.md CHANGED
@@ -1,36 +1,10 @@
1
- # Web App of Meta's META's Massively Multilingual Speech (MMS)
2
-
3
- This repository contains a Python code that implements a [META's Massively Multilingual Speech (MMS)](https://github.com/facebookresearch/fairseq/tree/main/examples/mms) using the Gradio library. The application allows users to record audio and convert it to text, or enter text and generate corresponding local speech output.
4
-
5
- ## Step 1: Clone repo
6
- ```shell
7
- git clone https://github.com/ikequan/meta-mms.git
8
- cd meta-mms
9
- ```
10
- ## Step 2: Prerequisites
11
-
12
- Before running the code, make sure you have the following requirements installed:
13
-
14
- - Python 3.x
15
- - gradio
16
- - speech_recognition
17
- - ttsmms
18
- - deep_translator
19
-
20
- You can install the required packages using the following command:
21
-
22
- ```shell
23
- pip install gradio SpeechRecognition ttsmms deep_translator
24
- ```
25
-
26
- ## Step 3: Download language model
27
- Check [here](https://github.com/wannaphong/ttsmms/blob/main/support_list.txt) for supported languages and their iso code for this step.
28
- ```shell
29
- curl https://dl.fbaipublicfiles.com/mms/tts/{put your language iso code here}.tar.gz --output {put your language iso code here}.tar.gz # Update lang
30
- mkdir -p data && tar -xzf {put your language iso code here}.tar.gz -C data/ # Update langcode
31
- ```
32
-
33
- ## Step 4: Run code
34
- ```shell
35
- python app.py
36
- ```
 
1
+ ---
2
+ title: English to Twi - Ewe Speech Generator
3
+ emoji: 🎤
4
+ colorFrom: blue
5
+ colorTo: yellow
6
+ sdk: gradio
7
+ sdk_version: 3.32.0
8
+ app_file: app.py
9
+ pinned: false
10
+ ---