Leopard Speech-to-Text
Python Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• NVIDIA Jetson Nano
• Raspberry Pi (3, 4)

Requirements

• Picovoice Account & AccessKey
• Python 3
• PIP

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Install Python 3 .

2. Install the pvleopard Python package using PIP:

pip3 install pvleopard

Usage

Create an instance of the engine and transcribe an audio file:

import pvleopard

leopard = pvleopard.create(access_key='${ACCESS_KEY}')

transcript, words = leopard.process_file('${AUDIO_PATH}')
print(transcript)
for word in words:
    print(
      "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f}"
      % (word.word, word.start_sec, word.end_sec, word.confidence))

Transcribe raw audio data (sample rate of 16 kHz, 16-bit linearly encoded and 1 channel):

def get_audio_data():
   // get audio data

transcript, words = leopard.process(get_audio_data())
print(transcript)
for word in words:
    print(
      "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f}"
      % (word.word, word.start_sec, word.end_sec, word.confidence))

Free resources used by Leopard:

leopard.delete();

Demo

For the Leopard Python SDK, we offer demo applications that demonstrate how to use the Speech-to-Text engine on audio files.

Setup

Install the pvleoparddemo Python package using PIP:

pip3 install pvleoparddemo

This package installs command-line utilities for the Leopard Python demos.

Usage

Use the --help flag to see the usage options for the demo:

leopard_demo_file --help

Run the following command to transcribe an audio file:

leopard_demo_file --access_key ${ACCESS_KEY} \
                  --audio_paths ${AUDIO_PATH1} ${AUDIO_PATH2} ...

For more information on our Leopard demos for Python, head over to our GitHub repository .

Language Model

The Leopard Python SDK comes preloaded with a default English language model (.pv file). Default models for other supported languages can be found in the Leopard GitHub repository .

Create custom language models using the Picovoice Console . Here you can train language models with custom vocabulary and boost words in the existing vocabulary.

Pass in the .pv file via the model_path argument of the create() constructor:

handle = pvleopard.create(
    access_key='${ACCESS_KEY}',
    model_path='${MODEL_PATH}')

Resources