Model Terminal
wav2vec2-large-xlsr-53-russian
An open-source Russian automatic speech recognition (ASR) model that converts spoken Russian audio into text. Fine-tuned from Meta's wav2vec2-large-xlsr-53 on Common Voice 6.1 and CSS10 Russian speech data by independent researcher Jonatas Grosman. Source: supabase.
Value score
Not scored
Context
—
tokens
Max output
—
tokens
Price
—
Capability radar
Peer value bars
Identity
- Developer
- jonatasgrosman
- Openness
- —
- Modalities
- —
- Release
- —
- Knowledge cutoff
- —
- Deprecation
- —
- API docs
- —
Benchmarks
No benchmark scores yet.
Compare nearby
Pricing
- Input / 1M
- —
- Output / 1M
- —
- Speed
- —
