Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ This model for Croatian ASR is based on the [facebook/wav2vec2-xls-r-300m model]
|
|
| 20 |
|
| 21 |
If you use this model, please cite the following paper:
|
| 22 |
|
| 23 |
-
Nikola Ljubešić, Danijel Koržinek, Peter Rupnik, Ivo-Pavao Jazbec. ParlaSpeech-HR -- a freely available ASR dataset for Croatian bootstrapped from the ParlaMint corpus.
|
| 24 |
|
| 25 |
## Metrics
|
| 26 |
|
|
@@ -31,6 +31,7 @@ Evaluation is performed on the dev and test portions of the [ParlaSpeech-HR v1.0
|
|
| 31 |
|dev|0.0335|0.1046|
|
| 32 |
|test|0.0234|0.0761|
|
| 33 |
|
|
|
|
| 34 |
|
| 35 |
## Usage in `transformers`
|
| 36 |
|
| 20 |
|
| 21 |
If you use this model, please cite the following paper:
|
| 22 |
|
| 23 |
+
Nikola Ljubešić, Danijel Koržinek, Peter Rupnik, Ivo-Pavao Jazbec. ParlaSpeech-HR -- a freely available ASR dataset for Croatian bootstrapped from the ParlaMint corpus. http://www.lrec-conf.org/proceedings/lrec2022/workshops/ParlaCLARINIII/pdf/2022.parlaclariniii-1.16.pdf
|
| 24 |
|
| 25 |
## Metrics
|
| 26 |
|
| 31 |
|dev|0.0335|0.1046|
|
| 32 |
|test|0.0234|0.0761|
|
| 33 |
|
| 34 |
+
There are multiple models available, and in terms of CER and WER, the best-performing model is [wav2vec2-large-slavic-parlaspeech-hr-lm](https://huggingface.co/classla/wav2vec2-large-slavic-parlaspeech-hr-lm).
|
| 35 |
|
| 36 |
## Usage in `transformers`
|
| 37 |
|