SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix S2T example (#10741)

Browse Source
This commit is contained in:
Lysandre Debut
2021-03-16 08:55:07 -04:00
committed by GitHub
parent 813d730c46
commit 5dcc08f1df
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/model_doc/speech_to_text.rst
View File

@@ -58,7 +58,7 @@ be installed as follows: ``apt install libsndfile1-dev``
>>> import soundfile as sf >>> import soundfile as sf
>>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr") >>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
>>> processor = Speech2Textprocessor.from_pretrained("facebook/s2t-small-librispeech-asr") >>> processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
>>> def map_to_array(batch): >>> def map_to_array(batch):
... speech, _ = sf.read(batch["file"]) ... speech, _ = sf.read(batch["file"])
@@ -69,7 +69,7 @@ be installed as follows: ``apt install libsndfile1-dev``
>>> ds = ds.map(map_to_array) >>> ds = ds.map(map_to_array)
>>> inputs = processor(ds["speech"][0], sampling_rate=16_000, return_tensors="pt") >>> inputs = processor(ds["speech"][0], sampling_rate=16_000, return_tensors="pt")
>>> generated_ids = model.generate(input_ids=inputs["input_features"], attention_mask=inputs["attention_mask]) >>> generated_ids = model.generate(input_ids=inputs["input_features"], attention_mask=inputs["attention_mask"])
>>> transcription = processor.batch_decode(generated_ids) >>> transcription = processor.batch_decode(generated_ids)
@@ -90,7 +90,7 @@ be installed as follows: ``apt install libsndfile1-dev``
>>> import soundfile as sf >>> import soundfile as sf
>>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-medium-mustc-multilingual-st") >>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-medium-mustc-multilingual-st")
>>> processor = Speech2Textprocessor.from_pretrained("facebook/s2t-medium-mustc-multilingual-st") >>> processor = Speech2TextProcessor.from_pretrained("facebook/s2t-medium-mustc-multilingual-st")
>>> def map_to_array(batch): >>> def map_to_array(batch):
... speech, _ = sf.read(batch["file"]) ... speech, _ = sf.read(batch["file"])