You can deploy this model and start earning money today!

vokra/
wav2vec2-xlsr-53-espeak-cv-ft

Name: wav2vec2-xlsr-53-espeak-cv-ft
Availability: InStock

vokra

gguf

apache-2.0

Views

No views yet

wav2vec2-xlsr-53-espeak-cv-ft (Vokra GGUF)

Converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.

This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.

Files

File	Size	SHA-256
`wav2vec2-xlsr-53-espeak.restamped.gguf`	1204.9 MB	`e0ab99e877afe254f35d1223c48d9b4a2eec0cd618fe114ac69b51725dedf248`

Usage

bash

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o wav2vec2-xlsr-53-espeak.restamped.gguf \
  https://huggingface.co/vokra/wav2vec2-xlsr-53-espeak-cv-ft/resolve/main/wav2vec2-xlsr-53-espeak.restamped.gguf

vokra-cli run --model wav2vec2-xlsr-53-espeak.restamped.gguf --input input.wav

Provenance

Field	Value
Architecture	`wav2vec2_ctc`
Tensors	424
Upstream source	facebook/wav2vec2-xlsr-53-espeak-cv-ft
Upstream licence	`apache-2.0`
Licence class	`permissive`
Registry model id	`wav2vec2-xlsr-53-espeak-cv-ft`
Vokra GGUF schema	1
Converted by	vokra-core 0.1.0-alpha.0

Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.

Licence

The weights are distributed under apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Attribution required

Facebook AI Research (Wav2Vec2 XLSR-53 eSpeak-phoneme CTC fine-tune)

This licence obliges you to display the attribution above when you ship something built on these weights. Vokra surfaces it at runtime via vokra_model_attribution (C ABI) and a CLI banner.

Verifying this file

bash

shasum -a 256 wav2vec2-xlsr-53-espeak.restamped.gguf
# expect: e0ab99e877afe254f35d1223c48d9b4a2eec0cd618fe114ac69b51725dedf248