Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
librispeech_asr
Generated from Trainer
asr_seq2esq
Instructions to use patrickvonplaten/wav2vec2-2-bart-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use patrickvonplaten/wav2vec2-2-bart-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="patrickvonplaten/wav2vec2-2-bart-large")# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/wav2vec2-2-bart-large") model = AutoModelForSpeechSeq2Seq.from_pretrained("patrickvonplaten/wav2vec2-2-bart-large") - Notebooks
- Google Colab
- Kaggle
Commit ·
b8a94de
1
Parent(s): 7a03e88
Update config.json
Browse files- config.json +0 -20
config.json
CHANGED
|
@@ -77,26 +77,6 @@
|
|
| 77 |
"return_dict_in_generate": false,
|
| 78 |
"scale_embedding": false,
|
| 79 |
"sep_token_id": null,
|
| 80 |
-
"task_specific_params": {
|
| 81 |
-
"summarization": {
|
| 82 |
-
"length_penalty": 1.0,
|
| 83 |
-
"max_length": 128,
|
| 84 |
-
"min_length": 12,
|
| 85 |
-
"num_beams": 4
|
| 86 |
-
},
|
| 87 |
-
"summarization_cnn": {
|
| 88 |
-
"length_penalty": 2.0,
|
| 89 |
-
"max_length": 142,
|
| 90 |
-
"min_length": 56,
|
| 91 |
-
"num_beams": 4
|
| 92 |
-
},
|
| 93 |
-
"summarization_xsum": {
|
| 94 |
-
"length_penalty": 1.0,
|
| 95 |
-
"max_length": 62,
|
| 96 |
-
"min_length": 11,
|
| 97 |
-
"num_beams": 6
|
| 98 |
-
}
|
| 99 |
-
},
|
| 100 |
"temperature": 1.0,
|
| 101 |
"tie_encoder_decoder": false,
|
| 102 |
"tie_word_embeddings": true,
|
|
|
|
| 77 |
"return_dict_in_generate": false,
|
| 78 |
"scale_embedding": false,
|
| 79 |
"sep_token_id": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
"temperature": 1.0,
|
| 81 |
"tie_encoder_decoder": false,
|
| 82 |
"tie_word_embeddings": true,
|