Commit
•
a50ca49
1
Parent(s):
923303d
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,7 @@ It achieves the following results on the evaluation set:
|
|
| 44 |
|
| 45 |
- For experimentation and curiosity.
|
| 46 |
- Based on the paper [AXRIV](https://arxiv.org/abs/2212.04356) and [Benchmarking OpenAI Whisper for non-English ASR - Dan Shafer](https://blog.deepgram.com/benchmarking-openai-whisper-for-non-english-asr/), there is a performance bias towards certain languages and curated datasets.
|
|
|
|
| 47 |
|
| 48 |
## Training and evaluation data
|
| 49 |
|
|
|
|
| 44 |
|
| 45 |
- For experimentation and curiosity.
|
| 46 |
- Based on the paper [AXRIV](https://arxiv.org/abs/2212.04356) and [Benchmarking OpenAI Whisper for non-English ASR - Dan Shafer](https://blog.deepgram.com/benchmarking-openai-whisper-for-non-english-asr/), there is a performance bias towards certain languages and curated datasets.
|
| 47 |
+
- From the Whisper paper, am_et is a low resource language (Table E), with the WER results ranging from 120-229, based on model size. Whisper small WER=120.2, indicating more training time may improve the fine tuning.
|
| 48 |
|
| 49 |
## Training and evaluation data
|
| 50 |
|