Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v3", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
d8411bd
1
Parent(s): f0e19c5
Upload processor (#2)
Browse files- Upload processor (b634ee66a93a2f270ba8bfab680050a66dd096e4)
Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>
- special_tokens_map.json +1 -0
- tokenizer_config.json +2 -1
special_tokens_map.json
CHANGED
|
@@ -122,6 +122,7 @@
|
|
| 122 |
"rstrip": false,
|
| 123 |
"single_word": false
|
| 124 |
},
|
|
|
|
| 125 |
"unk_token": {
|
| 126 |
"content": "<|endoftext|>",
|
| 127 |
"lstrip": false,
|
|
|
|
| 122 |
"rstrip": false,
|
| 123 |
"single_word": false
|
| 124 |
},
|
| 125 |
+
"pad_token": "<|endoftext|>",
|
| 126 |
"unk_token": {
|
| 127 |
"content": "<|endoftext|>",
|
| 128 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -12988,8 +12988,9 @@
|
|
| 12988 |
"eos_token": "<|endoftext|>",
|
| 12989 |
"errors": "replace",
|
| 12990 |
"model_max_length": 1000000000000000019884624838656,
|
| 12991 |
-
"pad_token":
|
| 12992 |
"processor_class": "WhisperProcessor",
|
| 12993 |
"tokenizer_class": "WhisperTokenizer",
|
|
|
|
| 12994 |
"unk_token": "<|endoftext|>"
|
| 12995 |
}
|
|
|
|
| 12988 |
"eos_token": "<|endoftext|>",
|
| 12989 |
"errors": "replace",
|
| 12990 |
"model_max_length": 1000000000000000019884624838656,
|
| 12991 |
+
"pad_token": "<|endoftext|>",
|
| 12992 |
"processor_class": "WhisperProcessor",
|
| 12993 |
"tokenizer_class": "WhisperTokenizer",
|
| 12994 |
+
"trust_remote_code": false,
|
| 12995 |
"unk_token": "<|endoftext|>"
|
| 12996 |
}
|