Skip to main content

Simultaneous Speech-to-Speech Translation Without Aligned Data.

Project description

Hibiki-Zero

Hibiki-Zero is a real-time and multilingual speech translation model. It translates from French, Spanish, Portuguese and German to English: accurately, with low latency, high audio quality, and voice transfer.

https://github.com/user-attachments/assets/d533ec45-8d5e-4e41-886a-0b2d198be6f3

🤗 Hugging Face Model Card | ⚙️ Tech report | 📄 Paper | 🎧 More samples

Requirements

Hibiki-Zero is a 3B-parameter model and requires an NVIDIA GPU to run: 8 GB VRAM should work, 12 GB is safe.

Run the server

Hibiki-Zero comes with a server you can run to interact with Hibiki in real time. To run it, just use:

uv run hibiki-zero serve [--gradio-tunnel]

Then go to the URL displayed to try out Hibiki-Zero. The --gradio-tunnel flag will forward the server to a public URL that you can access from anywhere.

Run inference

If you'd like to run Hibiki-Zero on existing audio files, run:

uv run hibiki-zero generate [--file /path/to/my/audio.wav --file /path/to/another/audio.mp3]

Batch inference is supported, meaning you can run the model on multiple audio files at the same time.

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

hibiki_zero-0.0.3.tar.gz (7.2 MB view details)

Uploaded Source

Built Distribution

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

hibiki_zero-0.0.3-py3-none-any.whl (3.6 MB view details)

Uploaded Python 3

File details

Details for the file hibiki_zero-0.0.3.tar.gz.

File metadata

  • Download URL: hibiki_zero-0.0.3.tar.gz
  • Upload date:
  • Size: 7.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for hibiki_zero-0.0.3.tar.gz
Algorithm Hash digest
SHA256 967a4019d8adf7379f67974b695033fa938e78f93eef9812fb90dc1205584652
MD5 8e458da2d6a7fbfa47ca9267b24e1e6b
BLAKE2b-256 8b656633f9f8905ae77be64f5bc49dcd065a0f1c21818ca23017913659b0c023

See more details on using hashes here.

Provenance

The following attestation bundles were made for hibiki_zero-0.0.3.tar.gz:

Publisher: publish-package.yml on kyutai-labs/hibiki-zero

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file hibiki_zero-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: hibiki_zero-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 3.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for hibiki_zero-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 c63234791052c83f715ba51434f0922469b0e71add7c9f6239d9bd9e73430d76
MD5 bf1f3b8d4bf3ce6d1585f0bbef14aa48
BLAKE2b-256 d5107693b2b86e0975d21777ef58ea9455298077c67c9964e7ca925b336bfeda

See more details on using hashes here.

Provenance

The following attestation bundles were made for hibiki_zero-0.0.3-py3-none-any.whl:

Publisher: publish-package.yml on kyutai-labs/hibiki-zero

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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