Fix some doctests after PR 15775 (#20036)
* Add skip_special_tokens=True in some doctest * For T5 * Fix for speech_to_text.mdx Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
@@ -57,7 +57,7 @@ be installed as follows: `apt install libsndfile1-dev`
|
|||||||
>>> inputs = processor(ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt")
|
>>> inputs = processor(ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt")
|
||||||
>>> generated_ids = model.generate(inputs["input_features"], attention_mask=inputs["attention_mask"])
|
>>> generated_ids = model.generate(inputs["input_features"], attention_mask=inputs["attention_mask"])
|
||||||
|
|
||||||
>>> transcription = processor.batch_decode(generated_ids)
|
>>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
||||||
>>> transcription
|
>>> transcription
|
||||||
['mister quilter is the apostle of the middle classes and we are glad to welcome his gospel']
|
['mister quilter is the apostle of the middle classes and we are glad to welcome his gospel']
|
||||||
```
|
```
|
||||||
@@ -87,9 +87,9 @@ be installed as follows: `apt install libsndfile1-dev`
|
|||||||
... forced_bos_token_id=processor.tokenizer.lang_code_to_id["fr"],
|
... forced_bos_token_id=processor.tokenizer.lang_code_to_id["fr"],
|
||||||
... )
|
... )
|
||||||
|
|
||||||
>>> translation = processor.batch_decode(generated_ids)
|
>>> translation = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
||||||
>>> translation
|
>>> translation
|
||||||
["<lang:fr> (Vidéo) Si M. Kilder est l'apossible des classes moyennes, et nous sommes heureux d'être accueillis dans son évangile."]
|
["(Vidéo) Si M. Kilder est l'apossible des classes moyennes, et nous sommes heureux d'être accueillis dans son évangile."]
|
||||||
```
|
```
|
||||||
|
|
||||||
See the [model hub](https://huggingface.co/models?filter=speech_to_text) to look for Speech2Text checkpoints.
|
See the [model hub](https://huggingface.co/models?filter=speech_to_text) to look for Speech2Text checkpoints.
|
||||||
|
|||||||
@@ -285,7 +285,7 @@ The predicted tokens will then be placed between the sentinel tokens.
|
|||||||
>>> sequence_ids = model.generate(input_ids)
|
>>> sequence_ids = model.generate(input_ids)
|
||||||
>>> sequences = tokenizer.batch_decode(sequence_ids)
|
>>> sequences = tokenizer.batch_decode(sequence_ids)
|
||||||
>>> sequences
|
>>> sequences
|
||||||
['<pad> <extra_id_0> park offers<extra_id_1> the<extra_id_2> park.</s>']
|
['<pad><extra_id_0> park offers<extra_id_1> the<extra_id_2> park.</s>']
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -1334,7 +1334,7 @@ class Speech2TextForConditionalGeneration(Speech2TextPreTrainedModel):
|
|||||||
|
|
||||||
>>> generated_ids = model.generate(inputs=input_features)
|
>>> generated_ids = model.generate(inputs=input_features)
|
||||||
|
|
||||||
>>> transcription = processor.batch_decode(generated_ids)[0]
|
>>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||||||
>>> transcription
|
>>> transcription
|
||||||
'mister quilter is the apostle of the middle classes and we are glad to welcome his gospel'
|
'mister quilter is the apostle of the middle classes and we are glad to welcome his gospel'
|
||||||
```"""
|
```"""
|
||||||
|
|||||||
@@ -201,7 +201,7 @@ PT_QUESTION_ANSWERING_SAMPLE = r"""
|
|||||||
>>> answer_end_index = outputs.end_logits.argmax()
|
>>> answer_end_index = outputs.end_logits.argmax()
|
||||||
|
|
||||||
>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
|
>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
|
||||||
>>> tokenizer.decode(predict_answer_tokens)
|
>>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
|
||||||
{expected_output}
|
{expected_output}
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user