Automatic Speech Recognition
Safetensors
Xhosa
whisper
audio
wjbmattingly commited on
Commit
50db92e
1 Parent(s): addcf32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -12,6 +12,7 @@ widget:
12
  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
13
  datasets:
14
  - Beijuka/xhosa_parakeet_50hr
 
15
  metrics:
16
  - wer
17
  base_model: openai/whisper-small
@@ -24,7 +25,7 @@ license: apache-2.0
24
  This model is a fine-tuned version of OpenAI's Whisper-small, optimized for isiXhosa Automatic Speech Recognition (ASR). It has been trained on the NCHLT isiXhosa Speech Corpus to improve its performance on isiXhosa speech transcription tasks.
25
 
26
  ## Performance
27
- - Word Error Rate (WER): 32%
28
 
29
  ## Base Model
30
  - Name: openai/whisper-small
 
12
  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
13
  datasets:
14
  - Beijuka/xhosa_parakeet_50hr
15
+ - wjbmattingly/xhosa_merged_audio
16
  metrics:
17
  - wer
18
  base_model: openai/whisper-small
 
25
  This model is a fine-tuned version of OpenAI's Whisper-small, optimized for isiXhosa Automatic Speech Recognition (ASR). It has been trained on the NCHLT isiXhosa Speech Corpus to improve its performance on isiXhosa speech transcription tasks.
26
 
27
  ## Performance
28
+ - Word Error Rate (WER): 29.73%
29
 
30
  ## Base Model
31
  - Name: openai/whisper-small