speech-test
commited on
Commit
•
6940fb9
1
Parent(s):
93b743a
Recalculate metrics on the whole test set
Browse files
README.md
CHANGED
@@ -23,10 +23,10 @@ model-index:
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
-
value: 42.
|
27 |
---
|
28 |
|
29 |
-
# Wav2Vec2-Large-XLSR-53-
|
30 |
|
31 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Hungarian using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset.
|
32 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
@@ -94,7 +94,7 @@ processor = Wav2Vec2Processor.from_pretrained("anton-l/wav2vec2-large-xlsr-53-hu
|
|
94 |
model = Wav2Vec2ForCTC.from_pretrained("anton-l/wav2vec2-large-xlsr-53-hungarian")
|
95 |
model.to("cuda")
|
96 |
|
97 |
-
cv_test = pd.read_csv("cv-corpus-6.1-2020-12-11/hu/test.tsv", sep='
|
98 |
clips_path = "cv-corpus-6.1-2020-12-11/hu/clips/"
|
99 |
|
100 |
def clean_sentence(sent):
|
@@ -127,7 +127,7 @@ for i, row in tqdm(cv_test.iterrows(), total=cv_test.shape[0]):
|
|
127 |
print("WER: {:2f}".format(100 * wer.compute(predictions=preds, references=targets)))
|
128 |
```
|
129 |
|
130 |
-
**Test Result**: 42.
|
131 |
|
132 |
|
133 |
## Training
|
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
+
value: 42.26
|
27 |
---
|
28 |
|
29 |
+
# Wav2Vec2-Large-XLSR-53-Hungarian
|
30 |
|
31 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Hungarian using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset.
|
32 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
|
|
94 |
model = Wav2Vec2ForCTC.from_pretrained("anton-l/wav2vec2-large-xlsr-53-hungarian")
|
95 |
model.to("cuda")
|
96 |
|
97 |
+
cv_test = pd.read_csv("cv-corpus-6.1-2020-12-11/hu/test.tsv", sep='\\t')
|
98 |
clips_path = "cv-corpus-6.1-2020-12-11/hu/clips/"
|
99 |
|
100 |
def clean_sentence(sent):
|
|
|
127 |
print("WER: {:2f}".format(100 * wer.compute(predictions=preds, references=targets)))
|
128 |
```
|
129 |
|
130 |
+
**Test Result**: 42.26 %
|
131 |
|
132 |
|
133 |
## Training
|