kotoba-tech
/

kotoba-whisper-v1.0

Automatic Speech Recognition

hf-asr-leaderboard

Inference Endpoints

Model card Files Files and versions Community

asahi417 commited on Apr 18, 2024

Commit

6a1eb4a

·

verified ·

1 Parent(s): ffbf23c

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -205,7 +205,7 @@ pipe = pipeline(
     device=device,
 )
-# load sample audio (concatenate instances to creaete a long audio)
 dataset = load_dataset("japanese-asr/ja_asr.reazonspeech_test", split="test")
 dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
 sample = {"array": np.concatenate([i["array"] for i in dataset[:20]["audio"]]), "sampling_rate": dataset[0]['audio']['sampling_rate'], "path": "tmp"}
@@ -248,7 +248,7 @@ pipe = pipeline(
     device=device,
 )
-# load sample audio (concatenate instances to creaete a long audio)
 dataset = load_dataset("japanese-asr/ja_asr.reazonspeech_test", split="test")
 dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
 sample = {"array": np.concatenate([i["array"] for i in dataset[:20]["audio"]]), "sampling_rate": dataset[0]['audio']['sampling_rate'], "path": "tmp"}

     device=device,
 )
+# load sample audio (concatenate instances to create a long audio)
 dataset = load_dataset("japanese-asr/ja_asr.reazonspeech_test", split="test")
 dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
 sample = {"array": np.concatenate([i["array"] for i in dataset[:20]["audio"]]), "sampling_rate": dataset[0]['audio']['sampling_rate'], "path": "tmp"}
     device=device,
 )
+# load sample audio (concatenate instances to create a long audio)
 dataset = load_dataset("japanese-asr/ja_asr.reazonspeech_test", split="test")
 dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
 sample = {"array": np.concatenate([i["array"] for i in dataset[:20]["audio"]]), "sampling_rate": dataset[0]['audio']['sampling_rate'], "path": "tmp"}