Skip to main content

A Python client for interacting with Bhashini inference services (ASR, NMT, TTS).

Project description

bhashini-client

A simple Python client library for interacting with Bhashini inference APIs.
Currently supports:

  • ASR (Automatic Speech Recognition)
  • NMT (Machine Translation)
  • TTS (Text-to-Speech)

Installation

pip install bhashini-client

Example Usage

from bhashini_client import BhashiniClient

client = BhashiniClient(api_key="api-key")

# ASR basics
print(client.asr("https://example.com/audio.wav", "te"))

# ASR with explicit configuration
print(
    client.asr(
        "https://example.com/audio.wav",
        "te",
        serviceId="bhashini/ai4bharat/conformer-multilingual-asr",
        samplingRate=44100,
    )
)

# NMT with optional processors
print(
    client.nmt(
        "What are you doing?",
        "en",
        "hi",
        numTranslation="False",
        preProcessors=["glossary"],
        postProcessors=["glossary"],
    )
)

# TTS with preprocessing and file output
print(
    client.tts(
        "मेरा नाम विहिर है",
        "en",
        save_to="output_audio.wav",
        gender="female",
        preProcessors=["text-normalization"],
        postProcessors=["high-compression"],
    )
)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bhashini_client-0.1.4.tar.gz (7.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

bhashini_client-0.1.4-py3-none-any.whl (9.3 kB view details)

Uploaded Python 3

File details

Details for the file bhashini_client-0.1.4.tar.gz.

File metadata

  • Download URL: bhashini_client-0.1.4.tar.gz
  • Upload date:
  • Size: 7.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for bhashini_client-0.1.4.tar.gz
Algorithm Hash digest
SHA256 feaf83e7dfadaff99b1b2d00816bd1bf4c8ac6ab9b36e3ea23a29f8984a6d4c1
MD5 7729e1eb16c0e150b276ae1fe2dbf0bf
BLAKE2b-256 02c1c62a263d79794e4a85b11a905d60c83afdfe01e229f37e04569cf6e3b9a7

See more details on using hashes here.

File details

Details for the file bhashini_client-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for bhashini_client-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 09b4f1a1840fdce75ca694cdac270020ae6c9a4faed9276f7de1a7b9878c5981
MD5 4cd9b7e08cce32a0488c31ced31bf0a1
BLAKE2b-256 9f115435d9ee7b0385bfc1d955784d6f1fd8d9aee90b29a4af03fd3f6cd5290a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page