Commit
•
0a8142a
1
Parent(s):
d2f8541
Correct scripts
Browse files- README.md +2 -2
- get_ctc_tokenizer.py +1 -1
- run_spgispeech.sh +2 -2
README.md
CHANGED
@@ -11,9 +11,9 @@ To reproduce this run, first call `get_ctc_tokenizer.py` to train the CTC tokeni
|
|
11 |
```python
|
12 |
#!/usr/bin/env bash
|
13 |
python run_flax_speech_recognition_ctc.py \
|
14 |
-
--model_name_or_path="esc/wav2vec2-pretrained" \
|
15 |
--tokenizer_name="wav2vec2-ctc-spgispeech-tokenizer" \
|
16 |
-
--dataset_name="esc/esc-datasets" \
|
17 |
--dataset_config_name="spgispeech" \
|
18 |
--output_dir="./" \
|
19 |
--wandb_project="wav2vec2-ctc" \
|
|
|
11 |
```python
|
12 |
#!/usr/bin/env bash
|
13 |
python run_flax_speech_recognition_ctc.py \
|
14 |
+
--model_name_or_path="esc-benchmark/wav2vec2-pretrained" \
|
15 |
--tokenizer_name="wav2vec2-ctc-spgispeech-tokenizer" \
|
16 |
+
--dataset_name="esc-benchmark/esc-datasets" \
|
17 |
--dataset_config_name="spgispeech" \
|
18 |
--output_dir="./" \
|
19 |
--wandb_project="wav2vec2-ctc" \
|
get_ctc_tokenizer.py
CHANGED
@@ -19,7 +19,7 @@ tokenizer_name = f"wav2vec2-ctc-{dataset_name}-tokenizer"
|
|
19 |
cutoff_freq = 0.01
|
20 |
|
21 |
dataset = load_dataset(
|
22 |
-
"esc/esc-datasets",
|
23 |
dataset_name,
|
24 |
split=split,
|
25 |
use_auth_token=use_auth_token,
|
|
|
19 |
cutoff_freq = 0.01
|
20 |
|
21 |
dataset = load_dataset(
|
22 |
+
"esc-benchmark/esc-datasets",
|
23 |
dataset_name,
|
24 |
split=split,
|
25 |
use_auth_token=use_auth_token,
|
run_spgispeech.sh
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
#!/usr/bin/env bash
|
2 |
python run_flax_speech_recognition_ctc.py \
|
3 |
-
--model_name_or_path="esc/wav2vec2-pretrained" \
|
4 |
--tokenizer_name="wav2vec2-ctc-spgispeech-tokenizer" \
|
5 |
-
--dataset_name="esc/esc-datasets" \
|
6 |
--dataset_config_name="spgispeech" \
|
7 |
--output_dir="./" \
|
8 |
--wandb_project="wav2vec2-ctc" \
|
|
|
1 |
#!/usr/bin/env bash
|
2 |
python run_flax_speech_recognition_ctc.py \
|
3 |
+
--model_name_or_path="esc-benchmark/wav2vec2-pretrained" \
|
4 |
--tokenizer_name="wav2vec2-ctc-spgispeech-tokenizer" \
|
5 |
+
--dataset_name="esc-benchmark/esc-datasets" \
|
6 |
--dataset_config_name="spgispeech" \
|
7 |
--output_dir="./" \
|
8 |
--wandb_project="wav2vec2-ctc" \
|