KittenTTS 2

.gitattributes

@@ -0,0 +1,106 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+cpp/default/voices.json filter=lfs diff=lfs merge=lfs -text
+cpp/model-tq2_1.gguf filter=lfs diff=lfs merge=lfs -text
+cpp/student_w4/voices.json filter=lfs diff=lfs merge=lfs -text
+cpp/student_w8/voices.json filter=lfs diff=lfs merge=lfs -text
+lm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+voices/03_radio_dj_smooth_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/06_elderly_professor_wise_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/11_stern_military_officer_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/17_dramatic_stage_actor_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/18_warm_storyteller_cozy_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/21_warm_grandfather_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/22_elderly_grandmother_soft_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/24_gentle_librarian_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/29_soothing_nurse_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/42_distinguished_elderly_diplomat_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/43_hushed_museum_guide_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/46_grizzled_war_veteran_gravelly_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/48_gentle_yoga_instructor_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/54_dreamy_poet_soft_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/55_somber_historian_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/63_rumbling_blues_musician_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/73_hushed_museum_guide_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/76_weathered_radio_journalist_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/79_hushed_conspirator_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/80_regal_narrator_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/chatterbox_mtl_hi_hindi.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_controlled_fury_older_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_controlled_fury_young_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_exhausted_mechanic_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_grieving_young_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_hushed_young_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_joyful_irish_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_playful_professional_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_playful_smooth_young_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_southern_elderly_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/h3_tender_older_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_2_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_2_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_3_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_3_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_4_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_4_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_5_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/kitten_v08_voice_5_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_ar_arabic.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_de_german.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_es_spanish.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_fr_french.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_it_italian.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_pt_portuguese.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_ru_russian.wav filter=lfs diff=lfs merge=lfs -text
+voices/ml_voxcpm2_zh_chinese.wav filter=lfs diff=lfs merge=lfs -text
+voices/ar_arabic.wav filter=lfs diff=lfs merge=lfs -text
+voices/controlled_fury_older_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/controlled_fury_young_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/de_german.wav filter=lfs diff=lfs merge=lfs -text
+voices/es_spanish.wav filter=lfs diff=lfs merge=lfs -text
+voices/exhausted_mechanic_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/fr_french.wav filter=lfs diff=lfs merge=lfs -text
+voices/grieving_young_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/hi_hindi.wav filter=lfs diff=lfs merge=lfs -text
+voices/hushed_young_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/it_italian.wav filter=lfs diff=lfs merge=lfs -text
+voices/joyful_irish_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/playful_professional_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/playful_smooth_young_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/pt_portuguese.wav filter=lfs diff=lfs merge=lfs -text
+voices/ru_russian.wav filter=lfs diff=lfs merge=lfs -text
+voices/southern_elderly_female.wav filter=lfs diff=lfs merge=lfs -text
+voices/tender_older_male.wav filter=lfs diff=lfs merge=lfs -text
+voices/zh_chinese.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,163 @@
+---
+pipeline_tag: text-to-speech
+tags:
+  - text-to-speech
+  - voice-cloning
+  - multilingual
+---
+
+# KittenTTS 2
+
+A 1.7B speech language model with in-context voice cloning. It reads text and writes S3
+codec tokens, which a vocoder turns into 24 kHz audio.
+
+```bash
+pip install kittenml
+```
+
+```python
+from kittenml import KittenTTS
+import soundfile as sf
+
+m = KittenTTS("KittenML/kitten-tts-2")
+
+# a built-in voice
+audio = m.generate("One day, a little girl named Lily found a needle in her room.",
+                   voice="Bruno")
+
+# or clone one, from 5-30 seconds of a single speaker
+audio = m.generate("This is my own voice.", reference="my_voice.wav")
+
+sf.write("output.wav", audio, m.sample_rate)
+```
+
+Everything the model needs is in this repository, so no Hugging Face login is required.
+
+## Voices
+
+`m.available_voices` lists all 47. Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki
+and Leo are the same speakers as in KittenTTS 0.8, so existing code keeps working.
+
+Nine are named after a language rather than a person — Arabic, Chinese, French, German,
+Hindi, Italian, Portuguese, Russian, Spanish — and are how you reach those languages,
+since the voice is what carries the accent:
+
+```python
+m.generate("Guten Morgen. Ich wünsche dir einen wunderschönen Tag.",
+           voice="German", normalize=False)
+```
+
+Pass `normalize=False` for non-English text: the text normalizer is English-tuned and
+will mangle numbers and dates in other languages.
+
+## Expression controls
+
+> **Beta.** Emotion control steers delivery rather than guaranteeing it, and the effect
+> varies by voice and by sentence.
+
+```python
+m.generate("[joyful] We won the grant <laugh> I can (((hardly))) believe it!",
+           voice="Kiki", preset="expressive")
+```
+
+A leading `[emotion]` tag, inline `<event>` tags and `(((emphasis)))` spans reach the
+model as markup rather than being spoken, and switch on its expression conditioning.
+
+**Emotions** — one leading tag sets the emotion for the whole line:
+
+`[angry]` `[contemplative]` `[excited]` `[joyful]` `[mundane]`
+`[nervous]` `[sad]` `[stern]` `[surprised]` `[tender]`
+
+**Vocal events** — inline, anywhere in the line:
+
+`<gasp>` `<giggle>` `<growl>` `<gulp>` `<laugh>`
+`<pause>` `<scoff>` `<sigh>` `<sob>` `<um>`
+
+**Emphasis** — triple parentheses stress a word or short phrase:
+
+```python
+m.generate("I told you (((never))) to open that door.", voice="Victor")
+```
+
+Only these twenty tags are recognised. They are the most common of the many in the
+training data, so a rarer one such as `[reverent]` is spoken as ordinary text rather
+than treated as markup — as is anything else bracketed, like `section [3]` or `x < 5`.
+
+## Weight variants
+
+The language model ships in three packings of the same weights. `weights=` picks one;
+`model.available_weights` lists them.
+
+| `weights=` | On disk | |
+|---|---|---|
+| `"packed"` *(default)* | 954 MB | 1.58-bit ternary body, bf16 embedding. **Lossless** |
+| `"emb4"` | 469 MB | Same body in TL2, plus a 4-bit embedding. **Lossy** |
+| `"full"` | 3469 MB | Plain bf16 |
+
+```python
+m = KittenTTS("KittenML/kitten-tts-2", weights="emb4")
+```
+
+Only the variant you ask for is downloaded.
+
+`emb4` halves the download, and the saving is almost entirely the token embedding — 324M
+parameters that `packed` has to leave at bf16 because they are not ternary. Its transformer
+body is still bit-exact; the embedding is not, at L2 relative error 0.118 against bf16.
+Measured at export, that costs roughly a tenth of a point of perplexity on internal
+evaluations. Small, but it is the one lossy thing here, which is why `packed` stays the
+default.
+
+## Decoders
+
+Audio is decoded in two stages, and the first can be swapped for a smaller distilled
+student with weights packed to 4 or 8 bits:
+
+```python
+m = KittenTTS("KittenML/kitten-tts-2", decoder="student_w4")
+```
+
+| Decoder | Flow on disk | |
+|---|---|---|
+| `default` | 459 MB | Best quality |
+| `student_w4` | 39 MB | Distilled single-step student, weights packed to 4 bits |
+
+These trade fidelity for footprint, not for speed: quantisation shrinks storage and
+memory bandwidth, not arithmetic.
+
+## What is in here
+
+```
+lm/          the speech language model, plus its spk_proj speaker head
+speaker/     the speaker-embedding model used when cloning
+voices/      reference clips, transcripts, and precomputed embeddings
+decoders/    the optional 4-bit decoder
+cpp/         GGUF weights for the llama.cpp fork, see "Running on CPU"
+config.json  token layout, decode presets, voice and decoder indexes
+```
+
+The weights are 947 MiB: 910 MiB for the language model and 37 MiB for the decoder.
+A load pulls those rather than the whole repository, and only the decoder you ask for.
+
+The language model's linear weights are ternary — within every 128-wide group each
+value is exactly one of `{-scale, 0, +scale}` — so bf16 spends 16 bits to say one of
+three things. `lm/model-ternary.safetensors` packs them five trits to a byte, 1.6 bits
+per weight, with each group keeping its scale at full precision:
+
+| | |
+|---|---|
+| `lm/model.safetensors` | 3.47 GB, bf16 throughout |
+| `lm/model-ternary.safetensors` | **0.95 GB**, the same weights, 3.6x smaller |
+
+The packing is exact rather than approximate, so the two produce bit-identical audio.
+`config.json` points `lm_packed` at the smaller file and that is what gets downloaded;
+the full file stays for anything loading this with plain `transformers`.
+
+## Running on CPU
+
+KittenTTS 2 runs on CPU out of the box — `device` is auto-detected — but the fastest way
+is [kitten-tts-2-cpp](https://github.com/KittenML/kitten-tts-2-cpp), our llama.cpp fork.
+The `cpp/` directory here holds what it needs: the GGUF language model and its decoders.
+
+## Requirements
+
+Python 3.10 or later, and PyTorch.

config.json

@@ -0,0 +1,54 @@
+{
+  "type": "KITTEN2",
+  "lm_dir": "lm",
+  "voices": "voices/voices.json",
+  "speaker_embedding": "speaker/model.safetensors",
+  "dtype": "bf16",
+  "speaker_embedding_dim": 512,
+  "sample_rate": 24000,
+  "default_voice": "Bruno",
+  "default_preset": "stable",
+  "decoders": {
+    "student_w4": "decoders/student_w4.pt"
+  },
+  "default_decoder": "default",
+  "decode_presets": {
+    "stable": {
+      "temperature": 0.8,
+      "top_p": 0.8,
+      "top_k": 50,
+      "min_p": 0.0
+    },
+    "expressive": {
+      "temperature": 0.9,
+      "top_p": 0.9,
+      "top_k": 50,
+      "min_p": 0.0
+    }
+  },
+  "generation": {
+    "use_reference_prompt": true,
+    "repetition_window": 50,
+    "emotion_control": "{emo: 1}",
+    "chunk_chars": 380,
+    "chunk_min_chars": 130
+  },
+  "token_map": {
+    "audio_id_base": 151675,
+    "num_audio_tokens": 6561,
+    "speech_start_id": 151669,
+    "speech_end_id": 151670,
+    "text_start_id": 151671,
+    "text_end_id": 151672,
+    "start_id": 151673,
+    "stop_id": 151674,
+    "final_seg_id": 158236,
+    "reference_speech_start_id": 158237,
+    "reference_speech_end_id": 158238,
+    "reference_text_start_id": 158239,
+    "reference_text_end_id": 158240
+  },
+  "lm_packed": "lm/model-ternary.safetensors",
+  "lm_emb4": "lm/model-tl2-emb4.safetensors",
+  "default_weights": "packed"
+}

cpp/default/decoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67c1a700358695c780c64417328b74f4d6a71f7363df7cdbbcda6133d6096ae
+size 534310697

cpp/default/voices.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b3df3c7f74b85c67214d7544eef0ba46336f9a85c2265e1169be49469517cf
+size 32744538

cpp/model-tq2_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b348b85baf807d7a662eebb5e1ecab95891c915ccf87a31ad68c6f54ae08799
+size 1029076832

cpp/student_w4/decoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ea803ad46a87f876c1b3b02f05e93dad15e4d2b58eafeb34884f52cdec0268
+size 312339253

cpp/student_w4/voices.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947d3f85da00e6b9f591c456cf5dd14efcb16b2b5cf3418bc6ecc8a540a027b4
+size 13531605

cpp/student_w8/decoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5839b2c0aa12e907727383a9443dcc3bbe6912f0a4fd24a076ee9bad4457e5f
+size 312339253

cpp/student_w8/voices.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947d3f85da00e6b9f591c456cf5dd14efcb16b2b5cf3418bc6ecc8a540a027b4
+size 13531605

decoders/student_w4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e585c64b6e0d220c155b0a8ff2d3c1446e1c7b2c59800c38a11dc5aaf270560
+size 38817934

lm/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 158241
+}

lm/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

lm/model-ternary.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b45564bebc2371b1e413f52bdbb3b4081e2eec4bfc0e2abc6ffed24969d2587
+size 954467780

lm/model-tl2-emb4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345d8fb961c1b0a8127b0c4a00bc5ea9226288467d6cf522926dd2bf90b7b332
+size 492114403

lm/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01dc763ff30999bf0802a394f5163ceab774b5e67cc01e6d09a9f9e12a86a46b
+size 3469120704

lm/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    "<|speech_start|>",
+    "<|speech_end|>",
+    "<|text_start|>",
+    "<|text_end|>",
+    "[START]",
+    "[STOP]"
+  ],
+  "eos_token": {
+    "content": "<|speech_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

lm/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99644fcf19a9aff57b247b4e56fffe878c65d9c230d21a46caf9acf8f54d31d7
+size 12649770

speaker/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 CNRS
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

speaker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c435292860671aa96e94bd19fcea055241c8ef05548e1e441a659b2bfd79fad5
+size 17418240

voices/03_radio_dj_smooth_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3772dbee7b41748d142fffada9cf64237018f5cc4993c2094a39214f7a51e9
+size 3692

voices/03_radio_dj_smooth_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b697a2a9e0bd35fcf7e9d6a5fa11b2f9373be3ebd763cc46db441fe67ec41b9c
+size 531116

voices/06_elderly_professor_wise_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069ca100db5ccd472422dd29df6bf7328208db8bc744bd46d3c90961ab27dcc4
+size 3688

voices/06_elderly_professor_wise_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38e5ca2c40e0d4d5e7b59d00334dc447f4809e09718f49b642ea706f740071d
+size 529964

voices/11_stern_military_officer_female.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eea57c36ad15efb154fa5bdcd15504e943a14fee90bb86085386b33a996d183
+size 3692

voices/11_stern_military_officer_female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb58b54dd3ad454fa5e85be9773659373681e124b0eb30b9d46633568918620
+size 531116

voices/17_dramatic_stage_actor_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1e441a8b6b940a328c6207b415d1e89b94ba64cc119531b00d93231d3055a2
+size 3692

voices/17_dramatic_stage_actor_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21eaf5823db802197df93107d586d6aeaedd5dd2b536c51ffb5b2f37c6a09689
+size 531116

voices/18_warm_storyteller_cozy_female.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e660e6e8d4e31af50a3e241b410b84027271c3b91516f23c968f9e51067405a
+size 3692

voices/18_warm_storyteller_cozy_female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32dc6c7067b8abaee14a1c6710dbd65765d9d7ea64eb5e33ce6be4372986f0ca
+size 531116

voices/21_warm_grandfather_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9392a3ccb2e0b2c1c60abaa52bf95dc275724b5c8d6b579568be4f8ebee4439
+size 3688

voices/21_warm_grandfather_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca52bc6f1ab55ec4c3d492321753ee76b342402e77420e780722390c0cc8428
+size 529964

voices/22_elderly_grandmother_soft_female.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e492a34d2d1329d524e3255929049eaeb62ba9d2605ce9e6147e004c8044dcc
+size 3692

voices/22_elderly_grandmother_soft_female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1856dfe08e5e599e1f5e0639c7afc8ebd0fc1972fa53700d4b7eb0b11ffdbb
+size 531116

voices/24_gentle_librarian_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a14d4925350564b594190adb4611127a10f5a7194f4bd63cd0b659c9571494d
+size 3692

voices/24_gentle_librarian_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de81cc87e7ff5af2ba7792729a02936ae3eb3d0543a2231bf3c5882a5ab9a39
+size 531116

voices/29_soothing_nurse_female.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a929b252a2ee515bf86c1902bedf82cc497f3daf4d23359c257157d320a00f0f
+size 3688

voices/29_soothing_nurse_female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a640d4678a16f7785720ca4d5fa6401e4b7f259a9cd173ff838ce4202731c627
+size 529964

voices/42_distinguished_elderly_diplomat_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec517dc22c04a2281fd08f03b7e5883bd69ef2d9513f8875470e4fd77c0c786
+size 3688

voices/42_distinguished_elderly_diplomat_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b8bfcaffb0ce30eb1543179f286d7e6e959d86a0318849bf215ea1f9b0f84d
+size 529964

voices/43_hushed_museum_guide_female.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7bc2dea4cc2995c6422b57f4a5dcbf3a94f222598ebcb33c7c4d2300361009
+size 3692

voices/43_hushed_museum_guide_female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451fc5dad347c4645b7581f4efc9bc3d2a7014e327a2db42d8bc6a3d84071c21
+size 531116

voices/46_grizzled_war_veteran_gravelly_male.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed50bea1b19b13a9ee6ec638d7c294f51cdb4bb7c9135c00c409e9b071e4fd0
+size 3688

voices/46_grizzled_war_veteran_gravelly_male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978307fa34aa85b9160ad66852d5f240c46089a9cda864529e7e52a6dc2f771d
+size 529964

voices/48_gentle_yoga_instructor_female.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0d5ea2473addece1e26458985e3a028c29eb4332f7c9bcf6eae4082e531262
+size 3692

voices/48_gentle_yoga_instructor_female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07840cf43dbce4c0b0bcafa758a96a5850ee05faae22f2fe00971b2167950a3
+size 531116