Automatic Speech Recognition
Transformers
Safetensors
wavlm
audio
speech
ctc
phone-recognition
arpabet
Instructions to use huper29/huper_recognizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huper29/huper_recognizer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="huper29/huper_recognizer")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("huper29/huper_recognizer") model = AutoModelForCTC.from_pretrained("huper29/huper_recognizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add library name, pipeline tag, and links to paper and code
#2
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
base_model: microsoft/wavlm-large
|
|
|
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
- audio
|
| 6 |
- speech
|
|
@@ -13,7 +15,9 @@ tags:
|
|
| 13 |
# HuPER Recognizer (ARPAbet phone recognition)
|
| 14 |
|
| 15 |
A CTC phone recognizer fine-tuned from **WavLM-Large** that maps **16 kHz** speech audio to an **ARPAbet** phone sequence.
|
| 16 |
-
See the HuPER paper for details:
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Quickstart
|
| 19 |
|
|
@@ -54,4 +58,4 @@ for token_id in pred_ids:
|
|
| 54 |
prev = token_id
|
| 55 |
|
| 56 |
print(" ".join(phone_tokens))
|
| 57 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: microsoft/wavlm-large
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: mit
|
| 5 |
+
pipeline_tag: automatic-speech-recognition
|
| 6 |
tags:
|
| 7 |
- audio
|
| 8 |
- speech
|
|
|
|
| 15 |
# HuPER Recognizer (ARPAbet phone recognition)
|
| 16 |
|
| 17 |
A CTC phone recognizer fine-tuned from **WavLM-Large** that maps **16 kHz** speech audio to an **ARPAbet** phone sequence.
|
| 18 |
+
See the HuPER paper for details: [HuPER: A Human-Inspired Framework for Phonetic Perception](https://huggingface.co/papers/2602.01634).
|
| 19 |
+
|
| 20 |
+
Code: https://github.com/Berkeley-Speech-Group/HuPER.
|
| 21 |
|
| 22 |
## Quickstart
|
| 23 |
|
|
|
|
| 58 |
prev = token_id
|
| 59 |
|
| 60 |
print(" ".join(phone_tokens))
|
| 61 |
+
```
|