Update README.md
Browse files
README.md
CHANGED
@@ -191,10 +191,10 @@ Evaluation was done with the [Common Voice 7.0 Finnish test split](https://huggi
|
|
191 |
To evaluate this model, run the `eval.py` script in this repository:
|
192 |
|
193 |
```bash
|
194 |
-
python3 eval.py --model_id Finnish-NLP/wav2vec2-
|
195 |
```
|
196 |
|
197 |
-
This model (the
|
198 |
|
199 |
| | Model parameters | WER (with LM) | WER (without LM) | CER (with LM) | CER (without LM) |
|
200 |
|----------------------------------------------------|------------------|---------------|------------------|---------------|------------------|
|
@@ -208,10 +208,10 @@ This model (the third row of the table) achieves the following WER (Word Error R
|
|
208 |
To evaluate this model, run the `eval.py` script in this repository:
|
209 |
|
210 |
```bash
|
211 |
-
python3 eval.py --model_id Finnish-NLP/wav2vec2-
|
212 |
```
|
213 |
|
214 |
-
This model (the
|
215 |
|
216 |
| | Model parameters | WER (with LM) | WER (without LM) | CER (with LM) | CER (without LM) |
|
217 |
|----------------------------------------------------|------------------|---------------|------------------|---------------|------------------|
|
|
|
191 |
To evaluate this model, run the `eval.py` script in this repository:
|
192 |
|
193 |
```bash
|
194 |
+
python3 eval.py --model_id Finnish-NLP/wav2vec2-xlsr-300m-finnish-lm --dataset mozilla-foundation/common_voice_7_0 --config fi --split test
|
195 |
```
|
196 |
|
197 |
+
This model (the fourth row of the table) achieves the following WER (Word Error Rate) and CER (Character Error Rate) results compared to our other models and their parameter counts:
|
198 |
|
199 |
| | Model parameters | WER (with LM) | WER (without LM) | CER (with LM) | CER (without LM) |
|
200 |
|----------------------------------------------------|------------------|---------------|------------------|---------------|------------------|
|
|
|
208 |
To evaluate this model, run the `eval.py` script in this repository:
|
209 |
|
210 |
```bash
|
211 |
+
python3 eval.py --model_id Finnish-NLP/wav2vec2-xlsr-300m-finnish-lm --dataset mozilla-foundation/common_voice_9_0 --config fi --split test
|
212 |
```
|
213 |
|
214 |
+
This model (the fourth row of the table) achieves the following WER (Word Error Rate) and CER (Character Error Rate) results compared to our other models and their parameter counts:
|
215 |
|
216 |
| | Model parameters | WER (with LM) | WER (without LM) | CER (with LM) | CER (without LM) |
|
217 |
|----------------------------------------------------|------------------|---------------|------------------|---------------|------------------|
|