README: model card + training datasets (base + 336 >=44k) + source link
Browse files
README.md
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: neucodec
|
| 4 |
+
pipeline_tag: audio-to-audio
|
| 5 |
+
tags:
|
| 6 |
+
- neural-audio-codec
|
| 7 |
+
- neucodec
|
| 8 |
+
- 44100hz
|
| 9 |
+
- decoder-finetune
|
| 10 |
+
- speech
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# NeuCodec 44.1 kHz — decoder finetune (depth 20)
|
| 14 |
+
|
| 15 |
+
A **44.1 kHz decoder finetune** of [`neuphonic/neucodec`](https://huggingface.co/neuphonic/neucodec).
|
| 16 |
+
Only the **decoder** (Vocos backbone + ISTFT head, transformer **depth 20**) is trained to
|
| 17 |
+
reconstruct **44.1 kHz** audio. The **16 kHz acoustic/semantic encoders and the ResidualFSQ
|
| 18 |
+
codebook are frozen and completely unchanged** — the discrete codes are identical to base
|
| 19 |
+
NeuCodec, so this model is a drop-in higher-fidelity decoder.
|
| 20 |
+
|
| 21 |
+
- **Sample rate:** 44 100 Hz · **hop:** 882 · **50 tokens/sec**
|
| 22 |
+
- **Trainable:** decoder only (GAN: multi-period + spec discriminators; losses: multi-res mel + STFT + feature-matching + adversarial)
|
| 23 |
+
- **Frozen:** w2v-BERT semantic encoder, acoustic `CodecEnc`, `fc_prior`/`fc_post_a`, FSQ codebook
|
| 24 |
+
|
| 25 |
+
## 🔗 Source code
|
| 26 |
+
|
| 27 |
+
Training pipeline, configs and RunPod automation:
|
| 28 |
+
**https://github.com/Scicom-AI-Enterprise-Organization/neucodec-44k**
|
| 29 |
+
|
| 30 |
+
## Files
|
| 31 |
+
|
| 32 |
+
| file | what |
|
| 33 |
+
|---|---|
|
| 34 |
+
| `pytorch_model.bin` | decoder weights for **inference** (load with `NeuCodec.from_pretrained`) |
|
| 35 |
+
| `last.ckpt` | full PyTorch-Lightning checkpoint **with optimizer states + LR schedulers** for **resuming training** |
|
| 36 |
+
|
| 37 |
+
## Training data
|
| 38 |
+
|
| 39 |
+
Diverse, predominantly high-sample-rate human speech (no synthetic TTS). The **scale-up group is
|
| 40 |
+
SR-verified ≥ 44 kHz** (probed before inclusion); the base corpora are long-form conversational,
|
| 41 |
+
expressive and anechoic speech. Two groups:
|
| 42 |
+
|
| 43 |
+
### Base corpora (Malaysia-AI + expressive/anechoic speech)
|
| 44 |
+
|
| 45 |
+
| dataset | content |
|
| 46 |
+
|---|---|
|
| 47 |
+
| [`malaysia-ai/malaysian-podcast-youtube`](https://huggingface.co/datasets/malaysia-ai/malaysian-podcast-youtube) | Malay long-form conversational podcasts (~2,234 h) |
|
| 48 |
+
| [`malaysia-ai/singaporean-podcast-youtube`](https://huggingface.co/datasets/malaysia-ai/singaporean-podcast-youtube) | Singaporean English podcasts (~1,255 h) |
|
| 49 |
+
| [`malaysia-ai/Multilingual-TTS`](https://huggingface.co/datasets/malaysia-ai/Multilingual-TTS) | CommonVoice-sidon multilingual short clips |
|
| 50 |
+
| [`malaysia-ai/malaysian-cartoons-youtube`](https://huggingface.co/datasets/malaysia-ai/malaysian-cartoons-youtube) | 48 kHz cartoon dialogue (subset) |
|
| 51 |
+
| [`malaysia-ai/malaysian-movie-youtube`](https://huggingface.co/datasets/malaysia-ai/malaysian-movie-youtube) | 48 kHz Malay movie dialogue |
|
| 52 |
+
| [`ylacombe/expresso`](https://huggingface.co/datasets/ylacombe/expresso) | 48 kHz expressive read speech |
|
| 53 |
+
| [`nytopop/expresso-conversational`](https://huggingface.co/datasets/nytopop/expresso-conversational) | 48 kHz improvised dialogue |
|
| 54 |
+
| [EARS](https://github.com/facebookresearch/ears_dataset) | 48 kHz anechoic fullband (emotional / conversational / reading) |
|
| 55 |
+
|
| 56 |
+
### Scale-up: 336 verified ≥ 44 kHz datasets
|
| 57 |
+
|
| 58 |
+
To maximise acoustic diversity for the decoder (language-agnostic — the codebook is frozen),
|
| 59 |
+
training is scaled with **336 additional datasets** (162 at 48 kHz, 174 at 44.1 kHz), mirrored as
|
| 60 |
+
`<name>*audio.zip` in [`malaysia-ai/Multilingual-TTS`](https://huggingface.co/datasets/malaysia-ai/Multilingual-TTS)
|
| 61 |
+
and SR-verified ≥ 44 kHz. Original sources:
|
| 62 |
+
|
| 63 |
+
<details>
|
| 64 |
+
<summary>Full list of 336 ≥ 44 kHz source datasets</summary>
|
| 65 |
+
|
| 66 |
+
- [`1rsh/gujarati-f-openslr`](https://huggingface.co/datasets/1rsh/gujarati-f-openslr) — 48000 Hz
|
| 67 |
+
- [`Aashish17405/audio-dataset`](https://huggingface.co/datasets/Aashish17405/audio-dataset) — 48000 Hz
|
| 68 |
+
- [`Aashish17405/audio-dataset-300`](https://huggingface.co/datasets/Aashish17405/audio-dataset-300) — 48000 Hz
|
| 69 |
+
- [`Aashish17405/audio-dataset-shuffled-300`](https://huggingface.co/datasets/Aashish17405/audio-dataset-shuffled-300) — 48000 Hz
|
| 70 |
+
- [`Abdullah500/IndicTTS-Bengali`](https://huggingface.co/datasets/Abdullah500/IndicTTS-Bengali) — 48000 Hz
|
| 71 |
+
- [`Abdullah500/IndicTTS_BengaliOLD`](https://huggingface.co/datasets/Abdullah500/IndicTTS_BengaliOLD) — 48000 Hz
|
| 72 |
+
- [`adalat-ai/in22-legal`](https://huggingface.co/datasets/adalat-ai/in22-legal) — 48000 Hz
|
| 73 |
+
- [`ahmadafaneh/common-voice-18-arabic`](https://huggingface.co/datasets/ahmadafaneh/common-voice-18-arabic) — 48000 Hz
|
| 74 |
+
- [`AIDC-AI/CSEMOTIONS`](https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS) — 48000 Hz
|
| 75 |
+
- [`AJosh/audio-dataset`](https://huggingface.co/datasets/AJosh/audio-dataset) — 48000 Hz
|
| 76 |
+
- [`alexantonov/chuvash_voice`](https://huggingface.co/datasets/alexantonov/chuvash_voice) — 48000 Hz
|
| 77 |
+
- [`aliyzd95/common_voice_21_0_fa`](https://huggingface.co/datasets/aliyzd95/common_voice_21_0_fa) — 48000 Hz
|
| 78 |
+
- [`aliyzd95/common_voice_22_0_fa`](https://huggingface.co/datasets/aliyzd95/common_voice_22_0_fa) — 48000 Hz
|
| 79 |
+
- [`anian0707/hindi-tts-dataset`](https://huggingface.co/datasets/anian0707/hindi-tts-dataset) — 48000 Hz
|
| 80 |
+
- [`atlithor/talromur3_with_prompts`](https://huggingface.co/datasets/atlithor/talromur3_with_prompts) — 48000 Hz
|
| 81 |
+
- [`atlithor/talromur3_without_emotions`](https://huggingface.co/datasets/atlithor/talromur3_without_emotions) — 48000 Hz
|
| 82 |
+
- [`bilguun/cv-mn-24.0`](https://huggingface.co/datasets/bilguun/cv-mn-24.0) — 48000 Hz
|
| 83 |
+
- [`bookbot/slr72_dataset`](https://huggingface.co/datasets/bookbot/slr72_dataset) — 48000 Hz
|
| 84 |
+
- [`Chingkheinganba/IndicTTS_Manipuri`](https://huggingface.co/datasets/Chingkheinganba/IndicTTS_Manipuri) — 48000 Hz
|
| 85 |
+
- [`chuuhtetnaing/myanmar-speech-dataset-openslr-80`](https://huggingface.co/datasets/chuuhtetnaing/myanmar-speech-dataset-openslr-80) — 48000 Hz
|
| 86 |
+
- [`Cnam-LMSSC/vibravox_enhanced_by_EBEN`](https://huggingface.co/datasets/Cnam-LMSSC/vibravox_enhanced_by_EBEN) — 48000 Hz
|
| 87 |
+
- [`CraneAILabs/waxal-lug-clean`](https://huggingface.co/datasets/CraneAILabs/waxal-lug-clean) — 48000 Hz
|
| 88 |
+
- [`datahiveai/arabic-multidialect-emotional-speech-demo`](https://huggingface.co/datasets/datahiveai/arabic-multidialect-emotional-speech-demo) — 48000 Hz
|
| 89 |
+
- [`DatarrX/burmese-synthetic-speech-corpus`](https://huggingface.co/datasets/DatarrX/burmese-synthetic-speech-corpus) — 48000 Hz
|
| 90 |
+
- [`DDD-Cambodia/khm-asr-cultural`](https://huggingface.co/datasets/DDD-Cambodia/khm-asr-cultural) — 48000 Hz
|
| 91 |
+
- [`deepdml/igbo-dict`](https://huggingface.co/datasets/deepdml/igbo-dict) — 48000 Hz
|
| 92 |
+
- [`deepdml/igbo-dict-16khz`](https://huggingface.co/datasets/deepdml/igbo-dict-16khz) — 48000 Hz
|
| 93 |
+
- [`deepdml/igbo-dict-expansion`](https://huggingface.co/datasets/deepdml/igbo-dict-expansion) — 48000 Hz
|
| 94 |
+
- [`deepdml/igbo-dict-expansion-16khz`](https://huggingface.co/datasets/deepdml/igbo-dict-expansion-16khz) — 48000 Hz
|
| 95 |
+
- [`deepdml/openslr-32-hq-SA-languages`](https://huggingface.co/datasets/deepdml/openslr-32-hq-SA-languages) — 48000 Hz
|
| 96 |
+
- [`deepdml/openslr42-khmer-tts`](https://huggingface.co/datasets/deepdml/openslr42-khmer-tts) — 48000 Hz
|
| 97 |
+
- [`deepdml/openslr65-tamil`](https://huggingface.co/datasets/deepdml/openslr65-tamil) — 48000 Hz
|
| 98 |
+
- [`deepdml/openslr80-burmese`](https://huggingface.co/datasets/deepdml/openslr80-burmese) — 48000 Hz
|
| 99 |
+
- [`doof-ferb/fpt_fosd`](https://huggingface.co/datasets/doof-ferb/fpt_fosd) — 48000 Hz
|
| 100 |
+
- [`doof-ferb/infore1_25hours`](https://huggingface.co/datasets/doof-ferb/infore1_25hours) — 48000 Hz
|
| 101 |
+
- [`espnet/ace-kising-segments`](https://huggingface.co/datasets/espnet/ace-kising-segments) — 48000 Hz
|
| 102 |
+
- [`espnet/ace-opencpop-segments`](https://huggingface.co/datasets/espnet/ace-opencpop-segments) — 48000 Hz
|
| 103 |
+
- [`FatimahEmadEldin/alsanaa-emirati-arabic-asr`](https://huggingface.co/datasets/FatimahEmadEldin/alsanaa-emirati-arabic-asr) — 48000 Hz
|
| 104 |
+
- [`fluffypotatoes/f1-team-radio`](https://huggingface.co/datasets/fluffypotatoes/f1-team-radio) — 48000 Hz
|
| 105 |
+
- [`fosters/lagodny-tsmok-iury-zhygamont-output_original`](https://huggingface.co/datasets/fosters/lagodny-tsmok-iury-zhygamont-output_original) — 48000 Hz
|
| 106 |
+
- [`fosters/lagodny-tsmok-iury-zhygamont_all`](https://huggingface.co/datasets/fosters/lagodny-tsmok-iury-zhygamont_all) — 48000 Hz
|
| 107 |
+
- [`gauravparajuli/slr43`](https://huggingface.co/datasets/gauravparajuli/slr43) — 48000 Hz
|
| 108 |
+
- [`ggfox00000/stt-summre-fr-test`](https://huggingface.co/datasets/ggfox00000/stt-summre-fr-test) — 48000 Hz
|
| 109 |
+
- [`ggfox00000/stt-vibravox-fr-test`](https://huggingface.co/datasets/ggfox00000/stt-vibravox-fr-test) — 48000 Hz
|
| 110 |
+
- [`hanamizuki-ai/genshin-voice-v3.3-mandarin`](https://huggingface.co/datasets/hanamizuki-ai/genshin-voice-v3.3-mandarin) — 48000 Hz
|
| 111 |
+
- [`hanamizuki-ai/genshin-voice-v3.4-mandarin`](https://huggingface.co/datasets/hanamizuki-ai/genshin-voice-v3.4-mandarin) — 48000 Hz
|
| 112 |
+
- [`hanamizuki-ai/genshin-voice-v3.5-mandarin`](https://huggingface.co/datasets/hanamizuki-ai/genshin-voice-v3.5-mandarin) — 48000 Hz
|
| 113 |
+
- [`HeshamHaroon/arabic-msa-25k-saudi-male-tashkeel`](https://huggingface.co/datasets/HeshamHaroon/arabic-msa-25k-saudi-male-tashkeel) — 48000 Hz
|
| 114 |
+
- [`HeshamHaroon/Dahee7`](https://huggingface.co/datasets/HeshamHaroon/Dahee7) — 48000 Hz
|
| 115 |
+
- [`hezarai/common-voice-13-fa`](https://huggingface.co/datasets/hezarai/common-voice-13-fa) — 48000 Hz
|
| 116 |
+
- [`hosein-m/french_homophone_asr`](https://huggingface.co/datasets/hosein-m/french_homophone_asr) — 48000 Hz
|
| 117 |
+
- [`humyn-labs/Asian-High-Fidelity-ASR-Dataset`](https://huggingface.co/datasets/humyn-labs/Asian-High-Fidelity-ASR-Dataset) — 48000 Hz
|
| 118 |
+
- [`humyn-labs/LATAM-High-Fidelity-ASR`](https://huggingface.co/datasets/humyn-labs/LATAM-High-Fidelity-ASR) — 48000 Hz
|
| 119 |
+
- [`hypaai/Hypa-Speech-10k`](https://huggingface.co/datasets/hypaai/Hypa-Speech-10k) — 48000 Hz
|
| 120 |
+
- [`hypaai/Hypa_Fleurs`](https://huggingface.co/datasets/hypaai/Hypa_Fleurs) — 48000 Hz
|
| 121 |
+
- [`igidn/wuwa-voice-EN`](https://huggingface.co/datasets/igidn/wuwa-voice-EN) — 48000 Hz
|
| 122 |
+
- [`impriyanshu-garg00/IndicVoices-R_Hindi`](https://huggingface.co/datasets/impriyanshu-garg00/IndicVoices-R_Hindi) — 48000 Hz
|
| 123 |
+
- [`JacobLinCool/jl-speech`](https://huggingface.co/datasets/JacobLinCool/jl-speech) — 48000 Hz
|
| 124 |
+
- [`JeanKouss/ewe_bible_v2_tts`](https://huggingface.co/datasets/JeanKouss/ewe_bible_v2_tts) — 48000 Hz
|
| 125 |
+
- [`jspaulsen/vctk`](https://huggingface.co/datasets/jspaulsen/vctk) — 48000 Hz
|
| 126 |
+
- [`juanjucm/OpenHQ-SpeechT-GL-EN`](https://huggingface.co/datasets/juanjucm/OpenHQ-SpeechT-GL-EN) — 48000 Hz
|
| 127 |
+
- [`jzsues/genshin-voice-zh`](https://huggingface.co/datasets/jzsues/genshin-voice-zh) — 48000 Hz
|
| 128 |
+
- [`Kishor798/text_to_speech_dataset`](https://huggingface.co/datasets/Kishor798/text_to_speech_dataset) — 48000 Hz
|
| 129 |
+
- [`Kppwdfgu1/Hypa-Speech-10k`](https://huggingface.co/datasets/Kppwdfgu1/Hypa-Speech-10k) — 48000 Hz
|
| 130 |
+
- [`KrorngAI/fleurs_openslr42_mpwt`](https://huggingface.co/datasets/KrorngAI/fleurs_openslr42_mpwt) — 48000 Hz
|
| 131 |
+
- [`Kukedlc/openslr61-es-ar-full`](https://huggingface.co/datasets/Kukedlc/openslr61-es-ar-full) — 48000 Hz
|
| 132 |
+
- [`leduckhai/MultiMed`](https://huggingface.co/datasets/leduckhai/MultiMed) — 48000 Hz
|
| 133 |
+
- [`leduckhai/MultiMed-ST`](https://huggingface.co/datasets/leduckhai/MultiMed-ST) — 48000 Hz
|
| 134 |
+
- [`LeVy4/speech-to-text`](https://huggingface.co/datasets/LeVy4/speech-to-text) — 48000 Hz
|
| 135 |
+
- [`lilgoose777/nepali_speech_english_translation_shuffle_dataset`](https://huggingface.co/datasets/lilgoose777/nepali_speech_english_translation_shuffle_dataset) — 48000 Hz
|
| 136 |
+
- [`Lindarychwalski/pony-speech`](https://huggingface.co/datasets/Lindarychwalski/pony-speech) — 48000 Hz
|
| 137 |
+
- [`longhim99/khm-asr-cultural`](https://huggingface.co/datasets/longhim99/khm-asr-cultural) — 48000 Hz
|
| 138 |
+
- [`lyhourt-FSA/khm-asr-cultural`](https://huggingface.co/datasets/lyhourt-FSA/khm-asr-cultural) — 48000 Hz
|
| 139 |
+
- [`maikezu/dowis`](https://huggingface.co/datasets/maikezu/dowis) — 48000 Hz
|
| 140 |
+
- [`manassehzw/sna-manasseh-150-raw`](https://huggingface.co/datasets/manassehzw/sna-manasseh-150-raw) — 48000 Hz
|
| 141 |
+
- [`masuidrive/cv-corpus-17.0-zh-TW-client_id-grouped`](https://huggingface.co/datasets/masuidrive/cv-corpus-17.0-zh-TW-client_id-grouped) — 48000 Hz
|
| 142 |
+
- [`MatrixStudio/TTS-CCabNavMSC`](https://huggingface.co/datasets/MatrixStudio/TTS-CCabNavMSC) — 48000 Hz
|
| 143 |
+
- [`MatrixStudio/TTS-CFCabNavSC`](https://huggingface.co/datasets/MatrixStudio/TTS-CFCabNavSC) — 48000 Hz
|
| 144 |
+
- [`MatrixStudio/TTS-SCCusSerFSC`](https://huggingface.co/datasets/MatrixStudio/TTS-SCCusSerFSC) — 48000 Hz
|
| 145 |
+
- [`MatrixStudio/TTS-SCDuFSC`](https://huggingface.co/datasets/MatrixStudio/TTS-SCDuFSC) — 48000 Hz
|
| 146 |
+
- [`Max5ive/openslr-32-hq-SA-languages-Sesotho`](https://huggingface.co/datasets/Max5ive/openslr-32-hq-SA-languages-Sesotho) — 48000 Hz
|
| 147 |
+
- [`mazesmazes/jenny-mimi`](https://huggingface.co/datasets/mazesmazes/jenny-mimi) — 48000 Hz
|
| 148 |
+
- [`MikCil/f1-team-radio`](https://huggingface.co/datasets/MikCil/f1-team-radio) — 48000 Hz
|
| 149 |
+
- [`mohamedmou/DATASET-darija-ASR-clean`](https://huggingface.co/datasets/mohamedmou/DATASET-darija-ASR-clean) — 48000 Hz
|
| 150 |
+
- [`MohamedRashad/arabic-english-code-switching`](https://huggingface.co/datasets/MohamedRashad/arabic-english-code-switching) — 48000 Hz
|
| 151 |
+
- [`MohamedRashad/common-voice-18-arabic`](https://huggingface.co/datasets/MohamedRashad/common-voice-18-arabic) — 48000 Hz
|
| 152 |
+
- [`ngia/ASR_pulaar`](https://huggingface.co/datasets/ngia/ASR_pulaar) — 48000 Hz
|
| 153 |
+
- [`ntaquan0125/steinsgate-voice`](https://huggingface.co/datasets/ntaquan0125/steinsgate-voice) — 48000 Hz
|
| 154 |
+
- [`ntt123/VietBibleVox-aligned`](https://huggingface.co/datasets/ntt123/VietBibleVox-aligned) — 48000 Hz
|
| 155 |
+
- [`OmarAhmedSobhy/egyption-with-emotion-dataset`](https://huggingface.co/datasets/OmarAhmedSobhy/egyption-with-emotion-dataset) — 48000 Hz
|
| 156 |
+
- [`OmarAhmedSobhy/tts-egyption-dataset`](https://huggingface.co/datasets/OmarAhmedSobhy/tts-egyption-dataset) — 48000 Hz
|
| 157 |
+
- [`omersaidd/tts_ahmet_deniz_tur`](https://huggingface.co/datasets/omersaidd/tts_ahmet_deniz_tur) — 48000 Hz
|
| 158 |
+
- [`rahafvii/EGY2K`](https://huggingface.co/datasets/rahafvii/EGY2K) — 48000 Hz
|
| 159 |
+
- [`ranbirchabungbam/meiteimayek-audio-parallel-corpus`](https://huggingface.co/datasets/ranbirchabungbam/meiteimayek-audio-parallel-corpus) — 48000 Hz
|
| 160 |
+
- [`reapzor/neurologySTT`](https://huggingface.co/datasets/reapzor/neurologySTT) — 48000 Hz
|
| 161 |
+
- [`RikkaBotan/nyan-jenny-format`](https://huggingface.co/datasets/RikkaBotan/nyan-jenny-format) — 48000 Hz
|
| 162 |
+
- [`RobotsMali/transcription-scorer`](https://huggingface.co/datasets/RobotsMali/transcription-scorer) — 48000 Hz
|
| 163 |
+
- [`SachinTelecmi/tts-hindi-stts2`](https://huggingface.co/datasets/SachinTelecmi/tts-hindi-stts2) — 48000 Hz
|
| 164 |
+
- [`sartifyllc/Sukuma-Voices`](https://huggingface.co/datasets/sartifyllc/Sukuma-Voices) — 48000 Hz
|
| 165 |
+
- [`scriptaudio/f1-team-radio`](https://huggingface.co/datasets/scriptaudio/f1-team-radio) — 48000 Hz
|
| 166 |
+
- [`sdcsdccdsd/CSEMOTIONS`](https://huggingface.co/datasets/sdcsdccdsd/CSEMOTIONS) — 48000 Hz
|
| 167 |
+
- [`shoron08/irodori-refs-10k`](https://huggingface.co/datasets/shoron08/irodori-refs-10k) — 48000 Hz
|
| 168 |
+
- [`shreeshacharya/Dhravani`](https://huggingface.co/datasets/shreeshacharya/Dhravani) — 48000 Hz
|
| 169 |
+
- [`siddiqiya/ar-eg-dataset`](https://huggingface.co/datasets/siddiqiya/ar-eg-dataset) — 48000 Hz
|
| 170 |
+
- [`slprl/StressTest`](https://huggingface.co/datasets/slprl/StressTest) — 48000 Hz
|
| 171 |
+
- [`smcproject/MSC`](https://huggingface.co/datasets/smcproject/MSC) — 48000 Hz
|
| 172 |
+
- [`somu9/iisc_mono_hindi_female`](https://huggingface.co/datasets/somu9/iisc_mono_hindi_female) — 48000 Hz
|
| 173 |
+
- [`somu9/iitm_mono_hindi_female`](https://huggingface.co/datasets/somu9/iitm_mono_hindi_female) — 48000 Hz
|
| 174 |
+
- [`speech-uk/opentts-kateryna`](https://huggingface.co/datasets/speech-uk/opentts-kateryna) — 48000 Hz
|
| 175 |
+
- [`speech-uk/opentts-oleksa`](https://huggingface.co/datasets/speech-uk/opentts-oleksa) — 48000 Hz
|
| 176 |
+
- [`speech-uk/opentts-tetiana`](https://huggingface.co/datasets/speech-uk/opentts-tetiana) — 48000 Hz
|
| 177 |
+
- [`speech-uk/tts-crh-abibullah`](https://huggingface.co/datasets/speech-uk/tts-crh-abibullah) — 48000 Hz
|
| 178 |
+
- [`speech-uk/tts-crh-arslan`](https://huggingface.co/datasets/speech-uk/tts-crh-arslan) — 48000 Hz
|
| 179 |
+
- [`speech-uk/tts-crh-sevil`](https://huggingface.co/datasets/speech-uk/tts-crh-sevil) — 48000 Hz
|
| 180 |
+
- [`SPRINGLab/IndicTTS-Hindi`](https://huggingface.co/datasets/SPRINGLab/IndicTTS-Hindi) — 48000 Hz
|
| 181 |
+
- [`SPRINGLab/IndicTTS_Assamese`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Assamese) — 48000 Hz
|
| 182 |
+
- [`SPRINGLab/IndicTTS_Bengali`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Bengali) — 48000 Hz
|
| 183 |
+
- [`SPRINGLab/IndicTTS_Kannada`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Kannada) — 48000 Hz
|
| 184 |
+
- [`SPRINGLab/IndicTTS_Malayalam`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Malayalam) — 48000 Hz
|
| 185 |
+
- [`SPRINGLab/IndicTTS_Manipuri`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Manipuri) — 48000 Hz
|
| 186 |
+
- [`SPRINGLab/IndicTTS_Marathi`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Marathi) — 48000 Hz
|
| 187 |
+
- [`SPRINGLab/IndicTTS_Odia`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Odia) — 48000 Hz
|
| 188 |
+
- [`SPRINGLab/IndicTTS_Punjabi`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Punjabi) — 48000 Hz
|
| 189 |
+
- [`SPRINGLab/IndicTTS_Rajasthani`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Rajasthani) — 48000 Hz
|
| 190 |
+
- [`SPRINGLab/IndicTTS_Tamil`](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Tamil) — 48000 Hz
|
| 191 |
+
- [`SPRINGLab/IndicVoices-R_Hindi`](https://huggingface.co/datasets/SPRINGLab/IndicVoices-R_Hindi) — 48000 Hz
|
| 192 |
+
- [`srezas/farsi_voice_dataset`](https://huggingface.co/datasets/srezas/farsi_voice_dataset) — 48000 Hz
|
| 193 |
+
- [`SynDataLab-JA-Refs/Irodori-Ja-Spk1-10k`](https://huggingface.co/datasets/SynDataLab-JA-Refs/Irodori-Ja-Spk1-10k) — 48000 Hz
|
| 194 |
+
- [`SynDataLab-JA-Refs/Irodori-Ja-Spk2-10k`](https://huggingface.co/datasets/SynDataLab-JA-Refs/Irodori-Ja-Spk2-10k) — 48000 Hz
|
| 195 |
+
- [`SynDataLab-JA-Refs/Irodori-Ja-Spk3-10k`](https://huggingface.co/datasets/SynDataLab-JA-Refs/Irodori-Ja-Spk3-10k) — 48000 Hz
|
| 196 |
+
- [`SynDataLab-JA-Refs/Irodori-Ja-Spk4-10k`](https://huggingface.co/datasets/SynDataLab-JA-Refs/Irodori-Ja-Spk4-10k) — 48000 Hz
|
| 197 |
+
- [`SynDataLab-JA-Refs/irodori-refs-10k`](https://huggingface.co/datasets/SynDataLab-JA-Refs/irodori-refs-10k) — 48000 Hz
|
| 198 |
+
- [`SynDataLab-JA-Refs/irodori-refs-10k-v2`](https://huggingface.co/datasets/SynDataLab-JA-Refs/irodori-refs-10k-v2) — 48000 Hz
|
| 199 |
+
- [`SynDataLab-JA-Refs/irodori-tts-refs-12k`](https://huggingface.co/datasets/SynDataLab-JA-Refs/irodori-tts-refs-12k) — 48000 Hz
|
| 200 |
+
- [`SynDataLab-JA/Irodori-Ja-500M-v2-vs-600M-v3-compare-20`](https://huggingface.co/datasets/SynDataLab-JA/Irodori-Ja-500M-v2-vs-600M-v3-compare-20) — 48000 Hz
|
| 201 |
+
- [`synthbot/pony-singing`](https://huggingface.co/datasets/synthbot/pony-singing) — 48000 Hz
|
| 202 |
+
- [`synthbot/pony-speech`](https://huggingface.co/datasets/synthbot/pony-speech) — 48000 Hz
|
| 203 |
+
- [`Tamazight-NLP/TOSD`](https://huggingface.co/datasets/Tamazight-NLP/TOSD) — 48000 Hz
|
| 204 |
+
- [`thennal/GMaSC`](https://huggingface.co/datasets/thennal/GMaSC) — 48000 Hz
|
| 205 |
+
- [`thennal/indic_tts_ml`](https://huggingface.co/datasets/thennal/indic_tts_ml) — 48000 Hz
|
| 206 |
+
- [`thennal/msc`](https://huggingface.co/datasets/thennal/msc) — 48000 Hz
|
| 207 |
+
- [`Trelis/multimed-hard`](https://huggingface.co/datasets/Trelis/multimed-hard) — 48000 Hz
|
| 208 |
+
- [`trysem/indicvoices_r-ML`](https://huggingface.co/datasets/trysem/indicvoices_r-ML) — 48000 Hz
|
| 209 |
+
- [`ttthe/MultiMed`](https://huggingface.co/datasets/ttthe/MultiMed) — 48000 Hz
|
| 210 |
+
- [`tunis-ai/arabic_speech_corpus`](https://huggingface.co/datasets/tunis-ai/arabic_speech_corpus) — 48000 Hz
|
| 211 |
+
- [`vinaybabu/voice_tech_for_all_challenge_samples_output`](https://huggingface.co/datasets/vinaybabu/voice_tech_for_all_challenge_samples_output) — 48000 Hz
|
| 212 |
+
- [`voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans`](https://huggingface.co/datasets/voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans) — 48000 Hz
|
| 213 |
+
- [`voice-biomarkers/openslr-32-hq-SA-languages-isiXhosa`](https://huggingface.co/datasets/voice-biomarkers/openslr-32-hq-SA-languages-isiXhosa) — 48000 Hz
|
| 214 |
+
- [`voice-biomarkers/openslr-32-hq-SA-languages-Sesotho`](https://huggingface.co/datasets/voice-biomarkers/openslr-32-hq-SA-languages-Sesotho) — 48000 Hz
|
| 215 |
+
- [`voice-biomarkers/openslr-32-hq-SA-languages-Setswana`](https://huggingface.co/datasets/voice-biomarkers/openslr-32-hq-SA-languages-Setswana) — 48000 Hz
|
| 216 |
+
- [`vrclc/openslr63`](https://huggingface.co/datasets/vrclc/openslr63) — 48000 Hz
|
| 217 |
+
- [`wanasash/enwaucymraeg`](https://huggingface.co/datasets/wanasash/enwaucymraeg) — 48000 Hz
|
| 218 |
+
- [`worldboss/ewe_bible_v2_tts`](https://huggingface.co/datasets/worldboss/ewe_bible_v2_tts) — 48000 Hz
|
| 219 |
+
- [`worldboss/twi_bible_v2_tts`](https://huggingface.co/datasets/worldboss/twi_bible_v2_tts) — 48000 Hz
|
| 220 |
+
- [`yasalma/tat_hackathon_asr`](https://huggingface.co/datasets/yasalma/tat_hackathon_asr) — 48000 Hz
|
| 221 |
+
- [`Yehor/qirimtatar-tts`](https://huggingface.co/datasets/Yehor/qirimtatar-tts) — 48000 Hz
|
| 222 |
+
- [`ylacombe/english_dialects`](https://huggingface.co/datasets/ylacombe/english_dialects) — 48000 Hz
|
| 223 |
+
- [`ylacombe/google-chilean-spanish`](https://huggingface.co/datasets/ylacombe/google-chilean-spanish) — 48000 Hz
|
| 224 |
+
- [`ylacombe/google-tamil`](https://huggingface.co/datasets/ylacombe/google-tamil) — 48000 Hz
|
| 225 |
+
- [`ymoslem/CoVoST2-EN-AR`](https://huggingface.co/datasets/ymoslem/CoVoST2-EN-AR) — 48000 Hz
|
| 226 |
+
- [`ymoslem/Living-Audio-Irish`](https://huggingface.co/datasets/ymoslem/Living-Audio-Irish) — 48000 Hz
|
| 227 |
+
- [`zinc75/Vibravox_dummy`](https://huggingface.co/datasets/zinc75/Vibravox_dummy) — 48000 Hz
|
| 228 |
+
- [`8Opt/clotho-dev-sample`](https://huggingface.co/datasets/8Opt/clotho-dev-sample) — 44100 Hz
|
| 229 |
+
- [`aangelakis/STOMA`](https://huggingface.co/datasets/aangelakis/STOMA) — 44100 Hz
|
| 230 |
+
- [`adiren7/darija_speech_to_text`](https://huggingface.co/datasets/adiren7/darija_speech_to_text) — 44100 Hz
|
| 231 |
+
- [`ahmed220v/SCC22`](https://huggingface.co/datasets/ahmed220v/SCC22) — 44100 Hz
|
| 232 |
+
- [`AigizK/bashkort_tts_dataset`](https://huggingface.co/datasets/AigizK/bashkort_tts_dataset) — 44100 Hz
|
| 233 |
+
- [`aipanjab/speech-mendeley-pa`](https://huggingface.co/datasets/aipanjab/speech-mendeley-pa) — 44100 Hz
|
| 234 |
+
- [`ALEKAS/ToneBooksPlus-Grigorii`](https://huggingface.co/datasets/ALEKAS/ToneBooksPlus-Grigorii) — 44100 Hz
|
| 235 |
+
- [`alimetin/turkish-parliament-speech`](https://huggingface.co/datasets/alimetin/turkish-parliament-speech) — 44100 Hz
|
| 236 |
+
- [`amine-khelif/DuBLaB-en-fr-0.7`](https://huggingface.co/datasets/amine-khelif/DuBLaB-en-fr-0.7) — 44100 Hz
|
| 237 |
+
- [`amine-khelif/DuBLaB-en-fr-0.7-f-0.2`](https://huggingface.co/datasets/amine-khelif/DuBLaB-en-fr-0.7-f-0.2) — 44100 Hz
|
| 238 |
+
- [`amine-khelif/DuBLaB-en-fr-0.7-f-0.5`](https://huggingface.co/datasets/amine-khelif/DuBLaB-en-fr-0.7-f-0.5) — 44100 Hz
|
| 239 |
+
- [`amine-khelif/DuBLaB-en-fr-0.8`](https://huggingface.co/datasets/amine-khelif/DuBLaB-en-fr-0.8) — 44100 Hz
|
| 240 |
+
- [`Anilosan15/YouTube_Video_Transkriptleri_TR`](https://huggingface.co/datasets/Anilosan15/YouTube_Video_Transkriptleri_TR) — 44100 Hz
|
| 241 |
+
- [`AnonXx/Pidgin_ASR_Dataset_Combined`](https://huggingface.co/datasets/AnonXx/Pidgin_ASR_Dataset_Combined) — 44100 Hz
|
| 242 |
+
- [`anzorq/kbd_speech`](https://huggingface.co/datasets/anzorq/kbd_speech) — 44100 Hz
|
| 243 |
+
- [`archivartaunik/Jevanhielle_Zyhamont_outChecked`](https://huggingface.co/datasets/archivartaunik/Jevanhielle_Zyhamont_outChecked) — 44100 Hz
|
| 244 |
+
- [`archivartaunik/output4Checked`](https://huggingface.co/datasets/archivartaunik/output4Checked) — 44100 Hz
|
| 245 |
+
- [`Bateesa/rw-tts-dataset`](https://huggingface.co/datasets/Bateesa/rw-tts-dataset) — 44100 Hz
|
| 246 |
+
- [`beratcmn/jessica-076`](https://huggingface.co/datasets/beratcmn/jessica-076) — 44100 Hz
|
| 247 |
+
- [`bezzam/coraal`](https://huggingface.co/datasets/bezzam/coraal) — 44100 Hz
|
| 248 |
+
- [`Bretagne/Lingua_Libre_br`](https://huggingface.co/datasets/Bretagne/Lingua_Libre_br) — 44100 Hz
|
| 249 |
+
- [`BrunoHays/Bangor-Miami-Spanish-English-Corpus`](https://huggingface.co/datasets/BrunoHays/Bangor-Miami-Spanish-English-Corpus) — 44100 Hz
|
| 250 |
+
- [`cagataydev/vlm-voice-audio`](https://huggingface.co/datasets/cagataydev/vlm-voice-audio) — 44100 Hz
|
| 251 |
+
- [`CentificAIResearch/DialectalSpeech-ICL`](https://huggingface.co/datasets/CentificAIResearch/DialectalSpeech-ICL) — 44100 Hz
|
| 252 |
+
- [`changelinglab/speechaccentarchive-pr`](https://huggingface.co/datasets/changelinglab/speechaccentarchive-pr) — 44100 Hz
|
| 253 |
+
- [`chris-t-jansen/erasmian_greek_nt`](https://huggingface.co/datasets/chris-t-jansen/erasmian_greek_nt) — 44100 Hz
|
| 254 |
+
- [`Codyfederer/fttrtest`](https://huggingface.co/datasets/Codyfederer/fttrtest) — 44100 Hz
|
| 255 |
+
- [`Codyfederer/test3434234`](https://huggingface.co/datasets/Codyfederer/test3434234) — 44100 Hz
|
| 256 |
+
- [`Codyfederer/tretret34543`](https://huggingface.co/datasets/Codyfederer/tretret34543) — 44100 Hz
|
| 257 |
+
- [`CoRal-project/coral-tts`](https://huggingface.co/datasets/CoRal-project/coral-tts) — 44100 Hz
|
| 258 |
+
- [`corti/med-term`](https://huggingface.co/datasets/corti/med-term) — 44100 Hz
|
| 259 |
+
- [`ctaguchi/killkan`](https://huggingface.co/datasets/ctaguchi/killkan) — 44100 Hz
|
| 260 |
+
- [`czyzi0/pwr-azon-speech-dataset`](https://huggingface.co/datasets/czyzi0/pwr-azon-speech-dataset) — 44100 Hz
|
| 261 |
+
- [`czyzi0/the-mc-speech-dataset`](https://huggingface.co/datasets/czyzi0/the-mc-speech-dataset) — 44100 Hz
|
| 262 |
+
- [`D00Movenok/russian-glados-portal2`](https://huggingface.co/datasets/D00Movenok/russian-glados-portal2) — 44100 Hz
|
| 263 |
+
- [`daanbrugmans/ovb-huissen-1`](https://huggingface.co/datasets/daanbrugmans/ovb-huissen-1) — 44100 Hz
|
| 264 |
+
- [`data-lab-voice/echo-tts-en-benchmarks-v1`](https://huggingface.co/datasets/data-lab-voice/echo-tts-en-benchmarks-v1) — 44100 Hz
|
| 265 |
+
- [`DataStudio/Vietnamese_ASR_TestingData_Old`](https://huggingface.co/datasets/DataStudio/Vietnamese_ASR_TestingData_Old) — 44100 Hz
|
| 266 |
+
- [`EMINES/Tamazight-Speech-to-Arabic-Text`](https://huggingface.co/datasets/EMINES/Tamazight-Speech-to-Arabic-Text) — 44100 Hz
|
| 267 |
+
- [`fablevi/one_voice_FACEBOOK_PARQUET`](https://huggingface.co/datasets/fablevi/one_voice_FACEBOOK_PARQUET) — 44100 Hz
|
| 268 |
+
- [`farbodbij/persian-words`](https://huggingface.co/datasets/farbodbij/persian-words) — 44100 Hz
|
| 269 |
+
- [`fiifinketia/twi-trigrams-speech-text-parallel`](https://huggingface.co/datasets/fiifinketia/twi-trigrams-speech-text-parallel) — 44100 Hz
|
| 270 |
+
- [`fosters/ales-krautsevich-karotkaia-gistoryia-belarusi-uladzimir-lisouski-output_original`](https://huggingface.co/datasets/fosters/ales-krautsevich-karotkaia-gistoryia-belarusi-uladzimir-lisouski-output_original) — 44100 Hz
|
| 271 |
+
- [`fosters/ales-krautsevich-karotkaia-gistoryia-belarusi-uladzimir-lisouski_all`](https://huggingface.co/datasets/fosters/ales-krautsevich-karotkaia-gistoryia-belarusi-uladzimir-lisouski_all) — 44100 Hz
|
| 272 |
+
- [`fosters/ales_razanau_all`](https://huggingface.co/datasets/fosters/ales_razanau_all) — 44100 Hz
|
| 273 |
+
- [`fosters/ales_razanau_output_original`](https://huggingface.co/datasets/fosters/ales_razanau_output_original) — 44100 Hz
|
| 274 |
+
- [`fosters/ales_zhuk_praklytaya_lyubow_all`](https://huggingface.co/datasets/fosters/ales_zhuk_praklytaya_lyubow_all) — 44100 Hz
|
| 275 |
+
- [`fosters/ales_zhuk_praklytaya_lyubow_output_original`](https://huggingface.co/datasets/fosters/ales_zhuk_praklytaya_lyubow_output_original) — 44100 Hz
|
| 276 |
+
- [`fosters/anatol_vyartsinski_pesnya_pra_hleb_all`](https://huggingface.co/datasets/fosters/anatol_vyartsinski_pesnya_pra_hleb_all) — 44100 Hz
|
| 277 |
+
- [`fosters/anatol_vyartsinski_pesnya_pra_hleb_output_original`](https://huggingface.co/datasets/fosters/anatol_vyartsinski_pesnya_pra_hleb_output_original) — 44100 Hz
|
| 278 |
+
- [`fosters/andre_marua_pakaranne_zolatam_all`](https://huggingface.co/datasets/fosters/andre_marua_pakaranne_zolatam_all) — 44100 Hz
|
| 279 |
+
- [`fosters/andre_marua_pakaranne_zolatam_output_original`](https://huggingface.co/datasets/fosters/andre_marua_pakaranne_zolatam_output_original) — 44100 Hz
|
| 280 |
+
- [`fosters/Antuan_de_Sent-Ekziupiery_Planieta_ludziei_all`](https://huggingface.co/datasets/fosters/Antuan_de_Sent-Ekziupiery_Planieta_ludziei_all) — 44100 Hz
|
| 281 |
+
- [`fosters/Antuan_de_Sent-Ekziupiery_Planieta_ludziei_output_original`](https://huggingface.co/datasets/fosters/Antuan_de_Sent-Ekziupiery_Planieta_ludziei_output_original) — 44100 Hz
|
| 282 |
+
- [`fosters/astryd_lindgren_braty_lvinae_sertsa_all`](https://huggingface.co/datasets/fosters/astryd_lindgren_braty_lvinae_sertsa_all) — 44100 Hz
|
| 283 |
+
- [`fosters/astryd_lindgren_braty_lvinae_sertsa_output_original`](https://huggingface.co/datasets/fosters/astryd_lindgren_braty_lvinae_sertsa_output_original) — 44100 Hz
|
| 284 |
+
- [`fosters/bely_klyck_all`](https://huggingface.co/datasets/fosters/bely_klyck_all) — 44100 Hz
|
| 285 |
+
- [`fosters/dzhozef_redzyard_kipling_all`](https://huggingface.co/datasets/fosters/dzhozef_redzyard_kipling_all) — 44100 Hz
|
| 286 |
+
- [`fosters/dzhozef_redzyard_kipling_output_original`](https://huggingface.co/datasets/fosters/dzhozef_redzyard_kipling_output_original) — 44100 Hz
|
| 287 |
+
- [`fosters/dzintra_shultse_robertsik_all`](https://huggingface.co/datasets/fosters/dzintra_shultse_robertsik_all) — 44100 Hz
|
| 288 |
+
- [`fosters/dzintra_shultse_robertsik_output_original`](https://huggingface.co/datasets/fosters/dzintra_shultse_robertsik_output_original) — 44100 Hz
|
| 289 |
+
- [`fosters/ernest_heminguei_stary_chalavek_i_mora_all`](https://huggingface.co/datasets/fosters/ernest_heminguei_stary_chalavek_i_mora_all) — 44100 Hz
|
| 290 |
+
- [`fosters/ernest_heminguei_stary_chalavek_i_mora_output_original`](https://huggingface.co/datasets/fosters/ernest_heminguei_stary_chalavek_i_mora_output_original) — 44100 Hz
|
| 291 |
+
- [`fosters/eryh_maryya_remark_all`](https://huggingface.co/datasets/fosters/eryh_maryya_remark_all) — 44100 Hz
|
| 292 |
+
- [`fosters/eryh_maryya_remark_output_original`](https://huggingface.co/datasets/fosters/eryh_maryya_remark_output_original) — 44100 Hz
|
| 293 |
+
- [`fosters/eryh_raspe_prygody_barona_myunhau_zena_all`](https://huggingface.co/datasets/fosters/eryh_raspe_prygody_barona_myunhau_zena_all) — 44100 Hz
|
| 294 |
+
- [`fosters/eryh_raspe_prygody_barona_myunhau_zena_output_original`](https://huggingface.co/datasets/fosters/eryh_raspe_prygody_barona_myunhau_zena_output_original) — 44100 Hz
|
| 295 |
+
- [`fosters/genadz_pashkou_all`](https://huggingface.co/datasets/fosters/genadz_pashkou_all) — 44100 Hz
|
| 296 |
+
- [`fosters/genadz_pashkou_output_original`](https://huggingface.co/datasets/fosters/genadz_pashkou_output_original) — 44100 Hz
|
| 297 |
+
- [`fosters/iagan_frydryh_shyler_kubak_all`](https://huggingface.co/datasets/fosters/iagan_frydryh_shyler_kubak_all) — 44100 Hz
|
| 298 |
+
- [`fosters/iagan_frydryh_shyler_kubak_output_original`](https://huggingface.co/datasets/fosters/iagan_frydryh_shyler_kubak_output_original) — 44100 Hz
|
| 299 |
+
- [`fosters/iakub-kolas-kazki-zhytstsia-output_original`](https://huggingface.co/datasets/fosters/iakub-kolas-kazki-zhytstsia-output_original) — 44100 Hz
|
| 300 |
+
- [`fosters/iakub-kolas-kazki-zhytstsia_all`](https://huggingface.co/datasets/fosters/iakub-kolas-kazki-zhytstsia_all) — 44100 Hz
|
| 301 |
+
- [`fosters/ivan-melezh-podykh-navalnitsy-valer-budzevich-output_original`](https://huggingface.co/datasets/fosters/ivan-melezh-podykh-navalnitsy-valer-budzevich-output_original) — 44100 Hz
|
| 302 |
+
- [`fosters/ivan-melezh-podykh-navalnitsy-valer-budzevich_all`](https://huggingface.co/datasets/fosters/ivan-melezh-podykh-navalnitsy-valer-budzevich_all) — 44100 Hz
|
| 303 |
+
- [`fosters/ivan-melezh-zavei-snezhan-valer-budzevich-output_original`](https://huggingface.co/datasets/fosters/ivan-melezh-zavei-snezhan-valer-budzevich-output_original) — 44100 Hz
|
| 304 |
+
- [`fosters/ivan-melezh-zavei-snezhan-valer-budzevich_all`](https://huggingface.co/datasets/fosters/ivan-melezh-zavei-snezhan-valer-budzevich_all) — 44100 Hz
|
| 305 |
+
- [`fosters/ivan-navumenka-zhul-vern-output_original`](https://huggingface.co/datasets/fosters/ivan-navumenka-zhul-vern-output_original) — 44100 Hz
|
| 306 |
+
- [`fosters/ivan-navumenka-zhul-vern_all`](https://huggingface.co/datasets/fosters/ivan-navumenka-zhul-vern_all) — 44100 Hz
|
| 307 |
+
- [`fosters/ivan-ptashnikau-lvy-output_original`](https://huggingface.co/datasets/fosters/ivan-ptashnikau-lvy-output_original) — 44100 Hz
|
| 308 |
+
- [`fosters/ivan-ptashnikau-lvy_all`](https://huggingface.co/datasets/fosters/ivan-ptashnikau-lvy_all) — 44100 Hz
|
| 309 |
+
- [`fosters/ivan_navumenka_sasna_pry_daroze_all`](https://huggingface.co/datasets/fosters/ivan_navumenka_sasna_pry_daroze_all) — 44100 Hz
|
| 310 |
+
- [`fosters/ivan_navumenka_sasna_pry_daroze_output_original`](https://huggingface.co/datasets/fosters/ivan_navumenka_sasna_pry_daroze_output_original) — 44100 Hz
|
| 311 |
+
- [`fosters/ivan_ptashnikau_all`](https://huggingface.co/datasets/fosters/ivan_ptashnikau_all) — 44100 Hz
|
| 312 |
+
- [`fosters/ivan_ptashnikau_output_original`](https://huggingface.co/datasets/fosters/ivan_ptashnikau_output_original) — 44100 Hz
|
| 313 |
+
- [`fosters/ivan_shamyakin_sertsa_na_daloni_all`](https://huggingface.co/datasets/fosters/ivan_shamyakin_sertsa_na_daloni_all) — 44100 Hz
|
| 314 |
+
- [`fosters/ivan_shamyakin_sertsa_na_daloni_output_original`](https://huggingface.co/datasets/fosters/ivan_shamyakin_sertsa_na_daloni_output_original) — 44100 Hz
|
| 315 |
+
- [`fosters/ivan_shamyakin_tryvozhnae_shchastse_all`](https://huggingface.co/datasets/fosters/ivan_shamyakin_tryvozhnae_shchastse_all) — 44100 Hz
|
| 316 |
+
- [`fosters/ivan_shamyakin_tryvozhnae_shchastse_output_original`](https://huggingface.co/datasets/fosters/ivan_shamyakin_tryvozhnae_shchastse_output_original) — 44100 Hz
|
| 317 |
+
- [`fosters/knihi-be-arlou_tancy_nad_horadam_all`](https://huggingface.co/datasets/fosters/knihi-be-arlou_tancy_nad_horadam_all) — 44100 Hz
|
| 318 |
+
- [`fosters/knihi-be-arlou_tancy_nad_horadam_output_original`](https://huggingface.co/datasets/fosters/knihi-be-arlou_tancy_nad_horadam_output_original) — 44100 Hz
|
| 319 |
+
- [`fosters/kuzma_chorny_makarkavyh_volka_all`](https://huggingface.co/datasets/fosters/kuzma_chorny_makarkavyh_volka_all) — 44100 Hz
|
| 320 |
+
- [`fosters/kuzma_chorny_makarkavyh_volka_output_original`](https://huggingface.co/datasets/fosters/kuzma_chorny_makarkavyh_volka_output_original) — 44100 Hz
|
| 321 |
+
- [`fosters/kuzma_chorny_poshuki_buduchyni_all`](https://huggingface.co/datasets/fosters/kuzma_chorny_poshuki_buduchyni_all) — 44100 Hz
|
| 322 |
+
- [`fosters/kuzma_chorny_poshuki_buduchyni_output_original`](https://huggingface.co/datasets/fosters/kuzma_chorny_poshuki_buduchyni_output_original) — 44100 Hz
|
| 323 |
+
- [`fosters/kuzma_chorny_zyamlya_all`](https://huggingface.co/datasets/fosters/kuzma_chorny_zyamlya_all) — 44100 Hz
|
| 324 |
+
- [`fosters/kuzma_chorny_zyamlya_output_original`](https://huggingface.co/datasets/fosters/kuzma_chorny_zyamlya_output_original) — 44100 Hz
|
| 325 |
+
- [`fosters/legendy-i-padanni_all`](https://huggingface.co/datasets/fosters/legendy-i-padanni_all) — 44100 Hz
|
| 326 |
+
- [`fosters/legendy-i-padanni_original`](https://huggingface.co/datasets/fosters/legendy-i-padanni_original) — 44100 Hz
|
| 327 |
+
- [`fosters/maksim_tank_all`](https://huggingface.co/datasets/fosters/maksim_tank_all) — 44100 Hz
|
| 328 |
+
- [`fosters/maksim_tank_output_original`](https://huggingface.co/datasets/fosters/maksim_tank_output_original) — 44100 Hz
|
| 329 |
+
- [`fosters/mar_yan_duksa_all`](https://huggingface.co/datasets/fosters/mar_yan_duksa_all) — 44100 Hz
|
| 330 |
+
- [`fosters/mar_yan_duksa_output_original`](https://huggingface.co/datasets/fosters/mar_yan_duksa_output_original) — 44100 Hz
|
| 331 |
+
- [`fosters/raisa_baravikova_vasmiradkou_i_all`](https://huggingface.co/datasets/fosters/raisa_baravikova_vasmiradkou_i_all) — 44100 Hz
|
| 332 |
+
- [`fosters/raisa_baravikova_vasmiradkou_i_output_original`](https://huggingface.co/datasets/fosters/raisa_baravikova_vasmiradkou_i_output_original) — 44100 Hz
|
| 333 |
+
- [`fosters/raisa_baravikova_vershy_pra_kahanne_all`](https://huggingface.co/datasets/fosters/raisa_baravikova_vershy_pra_kahanne_all) — 44100 Hz
|
| 334 |
+
- [`fosters/raisa_baravikova_vershy_pra_kahanne_output_original`](https://huggingface.co/datasets/fosters/raisa_baravikova_vershy_pra_kahanne_output_original) — 44100 Hz
|
| 335 |
+
- [`fosters/shata_rustaveli_vitsyaz_u_tygravai_shkury_all`](https://huggingface.co/datasets/fosters/shata_rustaveli_vitsyaz_u_tygravai_shkury_all) — 44100 Hz
|
| 336 |
+
- [`fosters/shata_rustaveli_vitsyaz_u_tygravai_shkury_output_original`](https://huggingface.co/datasets/fosters/shata_rustaveli_vitsyaz_u_tygravai_shkury_output_original) — 44100 Hz
|
| 337 |
+
- [`fosters/stefan_tsvei_g_nyabachnaya_kalektsyya_all`](https://huggingface.co/datasets/fosters/stefan_tsvei_g_nyabachnaya_kalektsyya_all) — 44100 Hz
|
| 338 |
+
- [`fosters/stefan_tsvei_g_nyabachnaya_kalektsyya_output_original`](https://huggingface.co/datasets/fosters/stefan_tsvei_g_nyabachnaya_kalektsyya_output_original) — 44100 Hz
|
| 339 |
+
- [`fosters/taras_shau_chenka_vershy_paemy_all`](https://huggingface.co/datasets/fosters/taras_shau_chenka_vershy_paemy_all) — 44100 Hz
|
| 340 |
+
- [`fosters/taras_shau_chenka_vershy_paemy_output_original`](https://huggingface.co/datasets/fosters/taras_shau_chenka_vershy_paemy_output_original) — 44100 Hz
|
| 341 |
+
- [`fosters/uilyam_folkner_pah_verbeny_all`](https://huggingface.co/datasets/fosters/uilyam_folkner_pah_verbeny_all) — 44100 Hz
|
| 342 |
+
- [`fosters/uilyam_folkner_pah_verbeny_output_original`](https://huggingface.co/datasets/fosters/uilyam_folkner_pah_verbeny_output_original) — 44100 Hz
|
| 343 |
+
- [`fosters/uladzimir-karatkevich-dzikae-paliavanne-karalia-stakha-aleg-garbuz-output_original`](https://huggingface.co/datasets/fosters/uladzimir-karatkevich-dzikae-paliavanne-karalia-stakha-aleg-garbuz-output_original) — 44100 Hz
|
| 344 |
+
- [`fosters/uladzimir-karatkevich-dzikae-paliavanne-karalia-stakha-aleg-garbuz_all`](https://huggingface.co/datasets/fosters/uladzimir-karatkevich-dzikae-paliavanne-karalia-stakha-aleg-garbuz_all) — 44100 Hz
|
| 345 |
+
- [`fosters/vasil_bykau_all`](https://huggingface.co/datasets/fosters/vasil_bykau_all) — 44100 Hz
|
| 346 |
+
- [`fosters/vasil_bykau_output_original`](https://huggingface.co/datasets/fosters/vasil_bykau_output_original) — 44100 Hz
|
| 347 |
+
- [`fosters/vasil_zue_nok_syaliba_all`](https://huggingface.co/datasets/fosters/vasil_zue_nok_syaliba_all) — 44100 Hz
|
| 348 |
+
- [`fosters/vasil_zue_nok_syaliba_output_original`](https://huggingface.co/datasets/fosters/vasil_zue_nok_syaliba_output_original) — 44100 Hz
|
| 349 |
+
- [`fosters/viktar_prau_dzin_all`](https://huggingface.co/datasets/fosters/viktar_prau_dzin_all) — 44100 Hz
|
| 350 |
+
- [`fosters/viktar_prau_dzin_output_original`](https://huggingface.co/datasets/fosters/viktar_prau_dzin_output_original) — 44100 Hz
|
| 351 |
+
- [`fosters/yakub_kolas_novaya_zyamlya_all`](https://huggingface.co/datasets/fosters/yakub_kolas_novaya_zyamlya_all) — 44100 Hz
|
| 352 |
+
- [`fosters/yakub_kolas_novaya_zyamlya_output_original`](https://huggingface.co/datasets/fosters/yakub_kolas_novaya_zyamlya_output_original) — 44100 Hz
|
| 353 |
+
- [`fosters/yanka_bryl_ptushki_i_gne_zdy_all`](https://huggingface.co/datasets/fosters/yanka_bryl_ptushki_i_gne_zdy_all) — 44100 Hz
|
| 354 |
+
- [`fosters/yanka_bryl_ptushki_i_gne_zdy_output_original`](https://huggingface.co/datasets/fosters/yanka_bryl_ptushki_i_gne_zdy_output_original) — 44100 Hz
|
| 355 |
+
- [`fosters/yanka_sipakou_odzium_all`](https://huggingface.co/datasets/fosters/yanka_sipakou_odzium_all) — 44100 Hz
|
| 356 |
+
- [`fosters/yanka_sipakou_odzium_output_original`](https://huggingface.co/datasets/fosters/yanka_sipakou_odzium_output_original) — 44100 Hz
|
| 357 |
+
- [`futureDoctor/turkic_tts_dataset`](https://huggingface.co/datasets/futureDoctor/turkic_tts_dataset) — 44100 Hz
|
| 358 |
+
- [`ghananlpcommunity/asante-twi-bible-speech-phonemes`](https://huggingface.co/datasets/ghananlpcommunity/asante-twi-bible-speech-phonemes) — 44100 Hz
|
| 359 |
+
- [`ghananlpcommunity/twi-trigrams-speech-text-parallel`](https://huggingface.co/datasets/ghananlpcommunity/twi-trigrams-speech-text-parallel) — 44100 Hz
|
| 360 |
+
- [`grandhigh/sample-id`](https://huggingface.co/datasets/grandhigh/sample-id) — 44100 Hz
|
| 361 |
+
- [`grider-transwithai/nekopara-speech`](https://huggingface.co/datasets/grider-transwithai/nekopara-speech) — 44100 Hz
|
| 362 |
+
- [`hananeek2/STT-algerian-dialect`](https://huggingface.co/datasets/hananeek2/STT-algerian-dialect) — 44100 Hz
|
| 363 |
+
- [`hhim8826/japanese-anime-speech-v2-split`](https://huggingface.co/datasets/hhim8826/japanese-anime-speech-v2-split) — 44100 Hz
|
| 364 |
+
- [`humairawan/AnimeSpeech`](https://huggingface.co/datasets/humairawan/AnimeSpeech) — 44100 Hz
|
| 365 |
+
- [`jdapaah/asante-twi-bible`](https://huggingface.co/datasets/jdapaah/asante-twi-bible) — 44100 Hz
|
| 366 |
+
- [`joujiboi/kuroyukihime-speech`](https://huggingface.co/datasets/joujiboi/kuroyukihime-speech) — 44100 Hz
|
| 367 |
+
- [`kizuna-intelligence/AItuber-Persona-Voices-JA`](https://huggingface.co/datasets/kizuna-intelligence/AItuber-Persona-Voices-JA) — 44100 Hz
|
| 368 |
+
- [`langswap/dialogs-ru-emotional-conversations`](https://huggingface.co/datasets/langswap/dialogs-ru-emotional-conversations) — 44100 Hz
|
| 369 |
+
- [`MatrixStudio/TTS-SCFChilSC`](https://huggingface.co/datasets/MatrixStudio/TTS-SCFChilSC) — 44100 Hz
|
| 370 |
+
- [`metricv/tl-whisper`](https://huggingface.co/datasets/metricv/tl-whisper) — 44100 Hz
|
| 371 |
+
- [`Michel21/rick-sanchez`](https://huggingface.co/datasets/Michel21/rick-sanchez) — 44100 Hz
|
| 372 |
+
- [`MikhailT/hifi-tts`](https://huggingface.co/datasets/MikhailT/hifi-tts) — 44100 Hz
|
| 373 |
+
- [`MohamedRashad/SCC22`](https://huggingface.co/datasets/MohamedRashad/SCC22) — 44100 Hz
|
| 374 |
+
- [`MothersTongue/mother_tongue_dataset`](https://huggingface.co/datasets/MothersTongue/mother_tongue_dataset) — 44100 Hz
|
| 375 |
+
- [`msnowchanj/pvariant-EQ`](https://huggingface.co/datasets/msnowchanj/pvariant-EQ) — 44100 Hz
|
| 376 |
+
- [`Pragmaticl/Trys2`](https://huggingface.co/datasets/Pragmaticl/Trys2) — 44100 Hz
|
| 377 |
+
- [`Pragmaticl/TuyenVanHoa2`](https://huggingface.co/datasets/Pragmaticl/TuyenVanHoa2) — 44100 Hz
|
| 378 |
+
- [`Pragmaticl/TuyenVanHoa4`](https://huggingface.co/datasets/Pragmaticl/TuyenVanHoa4) — 44100 Hz
|
| 379 |
+
- [`Professor/kinyarwanda-tts-dataset-kin`](https://huggingface.co/datasets/Professor/kinyarwanda-tts-dataset-kin) — 44100 Hz
|
| 380 |
+
- [`ray0rf1re/GLaDOS-audio-v2`](https://huggingface.co/datasets/ray0rf1re/GLaDOS-audio-v2) — 44100 Hz
|
| 381 |
+
- [`sachin6624/malayalam-tts-pro-voice`](https://huggingface.co/datasets/sachin6624/malayalam-tts-pro-voice) — 44100 Hz
|
| 382 |
+
- [`shannonnonshan/ViMedCSS-Cop`](https://huggingface.co/datasets/shannonnonshan/ViMedCSS-Cop) — 44100 Hz
|
| 383 |
+
- [`ShoukanLabs/AniSpeech`](https://huggingface.co/datasets/ShoukanLabs/AniSpeech) — 44100 Hz
|
| 384 |
+
- [`SoufianeDahimi/Tamazight-ASR-Dataset-v2`](https://huggingface.co/datasets/SoufianeDahimi/Tamazight-ASR-Dataset-v2) — 44100 Hz
|
| 385 |
+
- [`sudoping01/bam-asr-benchmark`](https://huggingface.co/datasets/sudoping01/bam-asr-benchmark) — 44100 Hz
|
| 386 |
+
- [`SynDataLab-EN-Refs/echo-ref-speakers-4k-en`](https://huggingface.co/datasets/SynDataLab-EN-Refs/echo-ref-speakers-4k-en) — 44100 Hz
|
| 387 |
+
- [`SynDataLab-EN-Refs/tts-pretrain-refs-3k-mos`](https://huggingface.co/datasets/SynDataLab-EN-Refs/tts-pretrain-refs-3k-mos) — 44100 Hz
|
| 388 |
+
- [`SynDataLab-EN/EchoTTS-OmniVoice-En`](https://huggingface.co/datasets/SynDataLab-EN/EchoTTS-OmniVoice-En) — 44100 Hz
|
| 389 |
+
- [`tensorxt/ViMedCSS`](https://huggingface.co/datasets/tensorxt/ViMedCSS) — 44100 Hz
|
| 390 |
+
- [`Thorsten-Voice/TV-44kHz-Full`](https://huggingface.co/datasets/Thorsten-Voice/TV-44kHz-Full) — 44100 Hz
|
| 391 |
+
- [`timniel/Pidgin_ASR_Dataset_Combined`](https://huggingface.co/datasets/timniel/Pidgin_ASR_Dataset_Combined) — 44100 Hz
|
| 392 |
+
- [`trysem/malayalam-tts-pro-voice`](https://huggingface.co/datasets/trysem/malayalam-tts-pro-voice) — 44100 Hz
|
| 393 |
+
- [`TutlaytAI/kabyle_asr`](https://huggingface.co/datasets/TutlaytAI/kabyle_asr) — 44100 Hz
|
| 394 |
+
- [`TutlaytAI/Kabyle_ASR-En_Translation`](https://huggingface.co/datasets/TutlaytAI/Kabyle_ASR-En_Translation) — 44100 Hz
|
| 395 |
+
- [`TutlaytAI/Kabyle_ASR-Fr_Translation`](https://huggingface.co/datasets/TutlaytAI/Kabyle_ASR-Fr_Translation) — 44100 Hz
|
| 396 |
+
- [`vsisik/voice-dataset-lili`](https://huggingface.co/datasets/vsisik/voice-dataset-lili) — 44100 Hz
|
| 397 |
+
- [`wcwxyz/test-audio`](https://huggingface.co/datasets/wcwxyz/test-audio) — 44100 Hz
|
| 398 |
+
- [`WhissleAI/Meta_STT_ZH_AIShell3`](https://huggingface.co/datasets/WhissleAI/Meta_STT_ZH_AIShell3) — 44100 Hz
|
| 399 |
+
- [`yasalma/audiobooks`](https://huggingface.co/datasets/yasalma/audiobooks) — 44100 Hz
|
| 400 |
+
- [`ymoslem/BitesizeIrish-GA-EN`](https://huggingface.co/datasets/ymoslem/BitesizeIrish-GA-EN) — 44100 Hz
|
| 401 |
+
- [`yuriilaba/toronto-tv-ukrainian`](https://huggingface.co/datasets/yuriilaba/toronto-tv-ukrainian) — 44100 Hz
|
| 402 |
+
|
| 403 |
+
</details>
|
| 404 |
+
|
| 405 |
+
## Usage
|
| 406 |
+
|
| 407 |
+
```python
|
| 408 |
+
import torch, soundfile as sf
|
| 409 |
+
from neucodec import NeuCodec
|
| 410 |
+
|
| 411 |
+
model = NeuCodec.from_pretrained("Scicom-intl/neucodec-44k-d20")
|
| 412 |
+
model.eval().cuda()
|
| 413 |
+
|
| 414 |
+
# encode (16 kHz path, frozen) -> codes -> decode (44.1 kHz, this finetune)
|
| 415 |
+
codes = model.encode_code(input_waveform=wav_16k) # [B, 1, T], identical to base NeuCodec
|
| 416 |
+
recon_44k = model.decode_code(codes).cpu().numpy()[0, 0] # 44 100 Hz
|
| 417 |
+
sf.write("recon.wav", recon_44k, 44_100)
|
| 418 |
+
```
|
| 419 |
+
|
| 420 |
+
The discrete codes are **identical to base `neuphonic/neucodec`** — only the reconstruction
|
| 421 |
+
sample rate and fidelity differ.
|