Hugging Face's logo

esc-bench
/
wav2vec2-aed-common_voice

Automatic Speech Recognition
Transformers
JAX
English
speech-encoder-decoder
esb
Model card Files
xet
 Community
Sanchit Gandhi commited on
Commit
b4d031f
·
1 Parent(s): 7a2ca30

Correct scripts

Browse files
Files changed (2) hide show
  1. README.md +2 -2
  2. run_common_voice.sh +2 -2
README.md CHANGED
@@ -10,8 +10,8 @@ To reproduce this run, execute:
10
  ```python
11
  #!/usr/bin/env bash
12
  python run_flax_speech_recognition_seq2seq.py \
13
- --dataset_name="esc/esc-datasets" \
14
- --model_name_or_path="esc/wav2vec2-aed-pretrained" \
15
  --dataset_config_name="ami" \
16
  --output_dir="./" \
17
  --wandb_name="wav2vec2-aed-common-voice" \
 
10
  ```python
11
  #!/usr/bin/env bash
12
  python run_flax_speech_recognition_seq2seq.py \
13
+ --dataset_name="esc-benchmark/esc-datasets" \
14
+ --model_name_or_path="esc-benchmark/wav2vec2-aed-pretrained" \
15
  --dataset_config_name="ami" \
16
  --output_dir="./" \
17
  --wandb_name="wav2vec2-aed-common-voice" \
run_common_voice.sh CHANGED
@@ -1,7 +1,7 @@
1
  #!/usr/bin/env bash
2
  python run_flax_speech_recognition_seq2seq.py \
3
- --dataset_name="esc/esc-datasets" \
4
- --model_name_or_path="esc/wav2vec2-aed-pretrained" \
5
  --dataset_config_name="ami" \
6
  --output_dir="./" \
7
  --wandb_name="wav2vec2-aed-common-voice" \
 
1
  #!/usr/bin/env bash
2
  python run_flax_speech_recognition_seq2seq.py \
3
+ --dataset_name="esc-benchmark/esc-datasets" \
4
+ --model_name_or_path="esc-benchmark/wav2vec2-aed-pretrained" \
5
  --dataset_config_name="ami" \
6
  --output_dir="./" \
7
  --wandb_name="wav2vec2-aed-common-voice" \