Merge branch 'main' of https://huggingface.co/alexcleu/wav2vec2-large-xlsr-polish into main
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ tags:
|
|
9 |
- xlsr-fine-tuning-week
|
10 |
license: apache-2.0
|
11 |
model-index:
|
12 |
-
- name:
|
13 |
results:
|
14 |
- task:
|
15 |
name: Speech Recognition
|
@@ -21,8 +21,9 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Test WER
|
23 |
type: wer
|
24 |
-
value:xxx
|
25 |
---
|
|
|
26 |
# wav2vec2-large-xlsr-polish
|
27 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Polish using the [Common Voice](https://huggingface.co/datasets/common_voice)
|
28 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
@@ -64,7 +65,7 @@ wer = load_metric("wer")
|
|
64 |
processor = Wav2Vec2Processor.from_pretrained("alexcleu/wav2vec2-large-xlsr-polish")
|
65 |
model = Wav2Vec2ForCTC.from_pretrained("alexcleu/wav2vec2-large-xlsr-polish")
|
66 |
model.to("cuda")
|
67 |
-
chars_to_ignore_regex = '[
|
68 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
69 |
# Preprocessing the datasets.
|
70 |
# We need to read the aduio files as arrays
|
|
|
9 |
- xlsr-fine-tuning-week
|
10 |
license: apache-2.0
|
11 |
model-index:
|
12 |
+
- name: XLSR Wav2vec2 Large 53 Polish by Alex Leu
|
13 |
results:
|
14 |
- task:
|
15 |
name: Speech Recognition
|
|
|
21 |
metrics:
|
22 |
- name: Test WER
|
23 |
type: wer
|
24 |
+
value: xxx
|
25 |
---
|
26 |
+
|
27 |
# wav2vec2-large-xlsr-polish
|
28 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Polish using the [Common Voice](https://huggingface.co/datasets/common_voice)
|
29 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
|
|
65 |
processor = Wav2Vec2Processor.from_pretrained("alexcleu/wav2vec2-large-xlsr-polish")
|
66 |
model = Wav2Vec2ForCTC.from_pretrained("alexcleu/wav2vec2-large-xlsr-polish")
|
67 |
model.to("cuda")
|
68 |
+
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“]'
|
69 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
70 |
# Preprocessing the datasets.
|
71 |
# We need to read the aduio files as arrays
|