fixie-ai
/

ultravox-v0_3

Feature Extraction

Model card Files Files and versions Community

farzadab commited on Aug 13

Commit

e3e0769

•

1 Parent(s): 498d19e

Update README.md

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -90,9 +90,10 @@ The current version of Ultravox, when invoked with audio content, has a time-to-
 Check out the audio tab on [TheFastest.ai](https://thefastest.ai/?m=audio) for daily benchmarks and a comparison with other existing models.
 ## Evaluation
-|                   | Ultravox v0.2 | Ultravox v0.3 | Whisper-Llama3.1 | Llama3.1 (text-only) |
-|-------------------|---------------|---------------|------------------|----------------------|
-| en_de (BLEU)      | 12.07         | 22.68         | 24.89            | 31.95                |
-| es_en (BLEU)      | 15.17         | 24.10         | 28.67            | 38.28                |
-| LibriSpeech clean.test (WER) | 6.07 | 6.67 | 3.4 | - |

 Check out the audio tab on [TheFastest.ai](https://thefastest.ai/?m=audio) for daily benchmarks and a comparison with other existing models.
 ## Evaluation
+|                   | en_de (BLEU) | es_en (BLEU) | LibriSpeech clean.test (WER) |
+|:------------------|:-------------|:-------------|:----------------------------|
+| Ultravox v0.2     | 12.07        | 15.17        | 6.07                        |
+| **Ultravox v0.3** | 22.68        | 24.10        | 6.67                        |
+| Whisper-Llama3.1  | 24.89        | 28.67        | 3.4                         |
+| Llama3.1 (text-only) | 31.95     | 38.28        | -                           |