Automatic Speech Recognition
MLX
Rust
multilingual
nemotron3_5_asr
int8
streaming-asr
fastconformer
rnnt
Instructions to use wcamon/catcher-asr-mlx-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use wcamon/catcher-asr-mlx-int8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir catcher-asr-mlx-int8 wcamon/catcher-asr-mlx-int8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "blank_token": "<blank>", | |
| "default_num_lookahead_tokens": 3, | |
| "feature_extractor": { | |
| "feature_extractor_type": "NemotronAsrStreamingFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 512, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemphasis": 0.97, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "num_prompts": 128, | |
| "processor_class": "Nemotron3_5AsrProcessor", | |
| "prompt_dictionary": { | |
| "af-ZA": 54, | |
| "am-ET": 49, | |
| "ar": 7, | |
| "ar-AR": 7, | |
| "auto": 101, | |
| "ay-BO": 81, | |
| "az-AZ": 66, | |
| "bg": 30, | |
| "bg-BG": 30, | |
| "bn-IN": 36, | |
| "cs": 22, | |
| "cs-CZ": 22, | |
| "da": 25, | |
| "da-DK": 25, | |
| "de": 9, | |
| "de-DE": 9, | |
| "el": 21, | |
| "el-GR": 21, | |
| "en": 0, | |
| "en-GB": 1, | |
| "en-US": 0, | |
| "enGB": 1, | |
| "es": 3, | |
| "es-ES": 2, | |
| "es-US": 3, | |
| "esES": 2, | |
| "et": 60, | |
| "et-EE": 60, | |
| "fa-IR": 38, | |
| "fi": 26, | |
| "fi-FI": 26, | |
| "fr": 8, | |
| "fr-CA": 100, | |
| "fr-FR": 8, | |
| "gn-PY": 82, | |
| "gu-IN": 42, | |
| "ha-NG": 50, | |
| "haw-US": 97, | |
| "he-IL": 64, | |
| "hi": 6, | |
| "hi-HI": 6, | |
| "hi-IN": 6, | |
| "hr": 29, | |
| "hr-HR": 29, | |
| "hu": 23, | |
| "hu-HU": 23, | |
| "hy-AM": 68, | |
| "id-ID": 34, | |
| "ig-NG": 53, | |
| "it": 15, | |
| "it-IT": 15, | |
| "ja-JA": 10, | |
| "ja-JP": 10, | |
| "ka-GE": 67, | |
| "km-KH": 47, | |
| "kn-IN": 43, | |
| "ko": 14, | |
| "ko-KO": 14, | |
| "ko-KR": 14, | |
| "ku-TR": 65, | |
| "ky-KG": 71, | |
| "ln-CD": 58, | |
| "lt": 31, | |
| "lt-LT": 31, | |
| "lv": 61, | |
| "lv-LV": 61, | |
| "mi-NZ": 96, | |
| "ml-IN": 44, | |
| "mr-IN": 41, | |
| "ms-MY": 35, | |
| "mt-MT": 102, | |
| "nah-MX": 83, | |
| "nb": 103, | |
| "nb-NO": 103, | |
| "ne-NP": 46, | |
| "nl": 16, | |
| "nl-NL": 16, | |
| "nn": 104, | |
| "nn-NO": 104, | |
| "no": 27, | |
| "no-NO": 27, | |
| "ny-MW": 57, | |
| "or-KE": 59, | |
| "pl": 17, | |
| "pl-PL": 17, | |
| "pt": 13, | |
| "pt-BR": 12, | |
| "pt-PT": 13, | |
| "qu-PE": 80, | |
| "ro": 20, | |
| "ro-RO": 20, | |
| "ru": 11, | |
| "ru-RU": 11, | |
| "rw-RW": 55, | |
| "si-LK": 45, | |
| "sk": 28, | |
| "sk-SK": 28, | |
| "sl": 62, | |
| "sl-SI": 62, | |
| "sm-WS": 98, | |
| "so-SO": 56, | |
| "sv": 24, | |
| "sv-SE": 24, | |
| "sw-KE": 48, | |
| "ta-IN": 39, | |
| "te-IN": 40, | |
| "tg-TJ": 70, | |
| "th-TH": 32, | |
| "to-TO": 99, | |
| "tr": 18, | |
| "tr-TR": 18, | |
| "uk": 19, | |
| "uk-UA": 19, | |
| "ur-PK": 37, | |
| "uz-UZ": 69, | |
| "vi-VN": 33, | |
| "yo-NG": 52, | |
| "zh-CN": 4, | |
| "zh-TW": 5, | |
| "zh-ZH": 4, | |
| "zu-ZA": 51 | |
| }, | |
| "supported_num_lookahead_tokens": [ | |
| 3, | |
| 0, | |
| 6, | |
| 13 | |
| ] | |
| } | |