Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Description

This plugin adds Faster Whisper speech recognition to OpenVoiceOS. Faster Whisper is a fast inference engine for OpenAI's Whisper automatic speech recognition models.

The plugin also provides a language detection transformer for ovos-dinkum-listener.

Install

pip install ovos-stt-plugin-fasterwhisper

Models

The plugin supports these Whisper model names: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2, large-v3, large, distil-large-v2, distil-medium.en, distil-small.en, distil-large-v3.

You can also pass a full path to a local model, or a Hugging Face repo ID, for example projecte-aina/faster-whisper-large-v3-ca-3catparla.

To use a model that is not already in Faster Whisper format, convert it, or pick a compatible model on Hugging Face.

Configuration

This example configures the large-v3 model to run on GPU:

  "stt": {
    "module": "ovos-stt-plugin-fasterwhisper",
    "ovos-stt-plugin-fasterwhisper": {
        "model": "large-v3",
        "use_cuda": true,
        "compute_type": "float16",
        "beam_size": 5,
        "cpu_threads": 4
    }
  }

This example uses Faster Whisper for language detection. It works only with ovos-dinkum-listener.

  "listener": {
    "audio_transformers": {
        "ovos-audio-transformer-plugin-fasterwhisper": {
            "model": "small"
        }
    }
  }

Related projects

License

Apache-2.0

Download files

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

Source Distribution

ovos_stt_plugin_fasterwhisper-0.4.1a6.tar.gz (9.8 kB view details)

Uploaded Source

Built Distribution

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

File details

Details for the file ovos_stt_plugin_fasterwhisper-0.4.1a6.tar.gz.

File metadata

File hashes

Hashes for ovos_stt_plugin_fasterwhisper-0.4.1a6.tar.gz
Algorithm Hash digest
SHA256 551c4115190bf6f11cfee1cb62335f4b826182e9761d1d79cd271e4cab13c7a6
MD5 094165f063d58985b3f8976411e46f7e
BLAKE2b-256 a75e11d9ac33808fc62ad34d607bed6556be24b6a0268299ebb930ec0110d1aa

See more details on using hashes here.

File details

Details for the file ovos_stt_plugin_fasterwhisper-0.4.1a6-py3-none-any.whl.

File metadata

File hashes

Hashes for ovos_stt_plugin_fasterwhisper-0.4.1a6-py3-none-any.whl
Algorithm Hash digest
SHA256 6fd0be394809cd78a5a61b25f807e661009b9e934cbde1b5b7beaf6afc0b4d82
MD5 b79317a6976c6d72175aad357999b992
BLAKE2b-256 f55fa17da0cf4b99e4c9375fe8b33d7410c0822200f0c762570938da25c42d7f

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 Sentry Error logging StatusPage Status page