Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
asr
speech-recognition
fine-tuned
bengali
audio
Instructions to use Noobbbbb/whisper-tiny-bn-custom-spm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Noobbbbb/whisper-tiny-bn-custom-spm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Noobbbbb/whisper-tiny-bn-custom-spm")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Noobbbbb/whisper-tiny-bn-custom-spm") model = AutoModelForSpeechSeq2Seq.from_pretrained("Noobbbbb/whisper-tiny-bn-custom-spm") - Notebooks
- Google Colab
- Kaggle
| { | |
| "assistant_confidence_threshold": 0.4, | |
| "assistant_lookbehind": 10, | |
| "begin_suppress_tokens": [], | |
| "bos_token_id": 4, | |
| "decoder_start_token_id": 4, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "encoder_repetition_penalty": 1.0, | |
| "eos_token_id": [ | |
| 5 | |
| ], | |
| "epsilon_cutoff": 0.0, | |
| "eta_cutoff": 0.0, | |
| "forced_decoder_ids": [ | |
| [ | |
| 1, | |
| 7 | |
| ], | |
| [ | |
| 2, | |
| 9 | |
| ] | |
| ], | |
| "lang_to_id": {}, | |
| "length_penalty": 1.0, | |
| "max_length": 225, | |
| "min_length": 0, | |
| "no_repeat_ngram_size": 0, | |
| "num_assistant_tokens": 20, | |
| "num_assistant_tokens_schedule": "constant", | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "pad_token_id": 5, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict_in_generate": false, | |
| "suppress_tokens": [], | |
| "target_lookbehind": 10, | |
| "task_to_id": {}, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "transformers_version": "5.12.0", | |
| "typical_p": 1.0, | |
| "use_cache": true | |
| } | |