Instructions to use hf-internal-testing/processor_with_lm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/processor_with_lm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="hf-internal-testing/processor_with_lm")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("hf-internal-testing/processor_with_lm") model = AutoModelForCTC.from_pretrained("hf-internal-testing/processor_with_lm") - Notebooks
- Google Colab
- Kaggle
Commit ·
70f0f84
1
Parent(s): 03628f2
up
Browse files- alphabet.json +1 -0
- language_model/attrs.json +1 -0
- language_model/bugs_bunny_kenlm.arpa +3 -0
- language_model/unigrams.txt +4 -0
- preprocessor_config.json +1 -0
- vocab.json +1 -0
alphabet.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"labels": ["\u2047", " ", "", "<s>", "</s>", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k"], "is_bpe": false}
|
language_model/attrs.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/bugs_bunny_kenlm.arpa
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a536cf8aeb47427440eb213246d97be87a7f97adbfe72383fa20f52ce996ecd
|
| 3 |
+
size 169
|
language_model/unigrams.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
</s>
|
| 2 |
+
<s>
|
| 3 |
+
bugs
|
| 4 |
+
bunny
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"feature_size": 1, "padding_value": 0.0, "sampling_rate": 16000, "return_attention_mask": false, "do_normalize": true}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"|": 0, "<pad>": 1, "<unk>": 2, "<s>": 3, "</s>": 4, "a": 5, "b": 6, "c": 7, "d": 8, "e": 9, "f": 10, "g": 11, "h": 12, "i": 13, "j": 14, "k": 15}
|