Hugging Face's logo

esc-bench
/
whisper-aed-tedlium

English
esb
Model card Files Community
sanchit-gandhi HF staff commited on
Commit
88f844e
•
1 Parent(s): 151d65f

Correct scripts

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. run_tedlium.sh +1 -1
README.md CHANGED
@@ -2,16 +2,17 @@
2
  language:
3
  - en
4
  tags:
5
- - esc
6
  datasets:
7
- - tedlium
 
8
  ---
9
  To reproduce this run, execute:
10
  ```python
11
  #!/usr/bin/env bash
12
  CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_whisper.py \
13
  --model_name_or_path="medium.en" \
14
- --dataset_name="esc-benchmark/esc-datasets" \
15
  --dataset_config_name="tedlium" \
16
  --max_steps="2500" \
17
  --output_dir="./" \
 
2
  language:
3
  - en
4
  tags:
5
+ - esb
6
  datasets:
7
+ - esb/datasets
8
+ - LIUM/tedlium
9
  ---
10
  To reproduce this run, execute:
11
  ```python
12
  #!/usr/bin/env bash
13
  CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_whisper.py \
14
  --model_name_or_path="medium.en" \
15
+ --dataset_name="esb/datasets" \
16
  --dataset_config_name="tedlium" \
17
  --max_steps="2500" \
18
  --output_dir="./" \
run_tedlium.sh CHANGED
@@ -1,7 +1,7 @@
1
  #!/usr/bin/env bash
2
  CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_whisper.py \
3
  --model_name_or_path="medium.en" \
4
- --dataset_name="esc-benchmark/esc-datasets" \
5
  --dataset_config_name="tedlium" \
6
  --max_steps="2500" \
7
  --output_dir="./" \
 
1
  #!/usr/bin/env bash
2
  CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_whisper.py \
3
  --model_name_or_path="medium.en" \
4
+ --dataset_name="esb/datasets" \
5
  --dataset_config_name="tedlium" \
6
  --max_steps="2500" \
7
  --output_dir="./" \