Hugging Face's logo

mistralai
/
Voxtral-Small-24B-2507

Audio-Text-to-Text
Safetensors
vllm
voxtral
Model card Files
xet
Community
26
sanchit-gandhi commited on
Commit
99bce02
·
verified ·
1 Parent(s): c9a314d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -5
README.md CHANGED
@@ -41,14 +41,11 @@ Voxtral builds upon Mistral Small 3 with powerful audio understanding capabiliti
41
 
42
  ### Audio
43
 
44
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/FKBy7KZAoTR52A_ht-ZpL.png)
45
-
46
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/-DcHsAjwuY6kbduC5XBH2.png)
47
-
48
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/7tJgqCPczuJZ4cj2PZe59.png)
49
 
50
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/puASxtajF1lDeGYPrRK5y.png)
51
 
 
52
  ### Text
53
 
54
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/9i9jpA2OLwhYut_wet836.png)
 
41
 
42
  ### Audio
43
 
44
+ Average word error rate (WER) over the FLEURS, Mozilla Common Voice and Multilingual LibriSpeech benchmarks:
 
 
 
 
45
 
46
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/puASxtajF1lDeGYPrRK5y.png)
47
 
48
+
49
  ### Text
50
 
51
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/9i9jpA2OLwhYut_wet836.png)