Safetensors
Vietnamese
whisper
dqnguyen commited on
Commit
da2d9ae
·
verified ·
1 Parent(s): 995a44b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -11,7 +11,7 @@ language:
11
 
12
  # PhoASR-whisper-small: Vietnamese Automatic Speech Recognition - A Revisit
13
 
14
- > We introduce `PhoASR-whisper-small`, a Vietnamese automatic speech recognition model obtained by fine-tuning the multilingual `whisper-small` on a 3000-hour dataset (`PhoASR-3000h`). The model directly produces clean transcripts with reliable timestamps, punctuation and capitalization, eliminating the need for separate post-processing tools. Please **cite** our [PhoASR paper](https://aclanthology.org/2026.findings-eacl.345/) whenever `PhoASR-whisper-small` is used to produce published results or is incorporated into other software:
15
 
16
  @inproceedings{phoasr,
17
  title = {{Vietnamese Automatic Speech Recognition: A Revisit}},
@@ -24,7 +24,8 @@ language:
24
  ## Model Inference with `transformers`
25
 
26
  ```python
27
- # Installation: pip install transformers==4.48.0
 
28
  import torch
29
  from transformers import pipeline
30
 
@@ -45,8 +46,10 @@ print(f"Full Text: {result['text']}")
45
  print(result['chunks'])
46
  ```
47
 
 
 
48
  ## License/Terms of Use
49
- This model is released under the BSD 3-Clause Clear license and the Qualcomm responsible AI license: [https://www.qualcomm.com/site/responsible-ai-license](https://www.qualcomm.com/site/responsible-ai-license)
50
 
51
  ## Uses
52
  The model is intended for research and educational purposes.
 
11
 
12
  # PhoASR-whisper-small: Vietnamese Automatic Speech Recognition - A Revisit
13
 
14
+ > We introduce `PhoASR-whisper-small`, a Vietnamese automatic speech recognition model obtained by fine-tuning the multilingual `whisper-small` on a 3000-hour dataset (`PhoASR-3000h`). The model directly produces clean transcripts with reliable timestamps, punctuation and capitalization, eliminating the need for separate post-processing tools. Please **cite** our [PhoASR paper](https://aclanthology.org/2026.findings-eacl.345/) whenever `PhoASR-whisper-small` is used to produce published results or is incorporated into other software.
15
 
16
  @inproceedings{phoasr,
17
  title = {{Vietnamese Automatic Speech Recognition: A Revisit}},
 
24
  ## Model Inference with `transformers`
25
 
26
  ```python
27
+ # INSTALLATION: pip install transformers==4.48.0
28
+
29
  import torch
30
  from transformers import pipeline
31
 
 
46
  print(result['chunks'])
47
  ```
48
 
49
+ For more low-level control, please see [inference.py](https://huggingface.co/Qualcomm-AI-Research/PhoASR-whisper-small/blob/main/inference.py).
50
+
51
  ## License/Terms of Use
52
+ This model is released under the BSD 3-Clause Clear license and the Qualcomm responsible AI license: [https://www.qualcomm.com/site/responsible-ai-license](https://www.qualcomm.com/site/responsible-ai-license).
53
 
54
  ## Uses
55
  The model is intended for research and educational purposes.