Repack preset voices: renamed, tagged, previews now model-synthesized

.gitattributes

@@ -4,4 +4,3 @@
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.wav filter=lfs diff=lfs merge=lfs -text
-banner.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -15,6 +15,12 @@ tags:
   - voice-cloning
   - vietnamese-tts
   - tieng-viet
+# NOTE deliberately NO `datasets:` field. It is the only thing that populates
+# the Hub's cross-link, but the Hub renders it as "Models trained or fine-tuned
+# on <dataset>" — which for our own held-out benchmark reads as train/test
+# contamination. ZeroBench-TTS is EVALUATION data; every voice in it is held
+# out of training. The `model-index` block below states that correctly, and the
+# body links the benchmark in prose.
 metrics:
   - wer
 model-index:
@@ -135,10 +141,29 @@ for chunk in tts.synthesize_stream("Một đoạn văn bản dài hơn…", voic
 
 ## Benchmarks
 
-Measured on **[ZeroBench-TTS](https://huggingface.co/datasets/zeroweight-ai/ZeroBench-TTS)** 
+Measured on **[ZeroBench-TTS](https://huggingface.co/datasets/zeroweight-ai/ZeroBench-TTS)** —
+137 items, 59 held-out reference voices × 4 subsets — against
+[OmniVoice](https://huggingface.co/k2-fsa/OmniVoice) and the two public
+Vietnamese XTTS-v2 finetunes. 137/137 scored for every system, 0 empty
+generations. OmniVoice is given its optional `language="vi"` hint, which its
+model card recommends and which measurably helps it.
+
+**Scored by the benchmark, not by us.** ZeroTTS synthesizes the clips and hands
+them to `zerobench_eval`, the official scorer published inside the benchmark
+dataset repo. Nothing in this repo computes a metric.
+
+### Headline
 
 Every system reads **normalized text** — dates, numbers and acronyms already
-spoken out, from the benchmark's own curated reading. 
+spoken out, from the benchmark's own curated reading. Every system gets exactly
+the same input, so the comparison is like-for-like.
+
+This is the condition a Vietnamese TTS system meets in production, where a text
+frontend runs ahead of the model. ZeroTTS ships one — `normalize_vi_text`,
+applied by default (see the [GitHub README](https://github.com/zeroweight-ai/ZeroTTS#usage)) — which reproduces the benchmark's
+reading on 34 of the 35 items that need normalization. Neither baseline ships a
+Vietnamese frontend at all, which is why the raw-text table below is so much
+harsher on them.
 
 | | **ZeroTTS** | OmniVoice | XTTS-v2-vietnamse | viXTTS |
 |---|:-:|:-:|:-:|:-:|
@@ -181,6 +206,60 @@ with no Vietnamese text frontend faces.
 | `challenging` | acronyms, dates, %, currency | **1.75 %** | 4.46 % | 27.86 % | 31.85 % |
 | **overall** | | **1.03 %** | **4.13 %** | **16.42 %** | **18.40 %** |
 
+**Reading these fairly:**
+
+* **OmniVoice beats us on two things, and they are worth naming.** Its speaker
+  similarity is the best of the four (0.951 vs our 0.938), and on `code_switch`
+  it is roughly half our error rate (0.46 % vs 0.95 %). If cloning fidelity or
+  English-in-Vietnamese is your priority, it is a genuinely strong option — at
+  3.1 GB on a GPU.
+* **OmniVoice's overall figure is dominated by one subset.** `cross_lingual`
+  (foreign voice prompt, Vietnamese text) costs it 17.71 % raw against our
+  1.42 %, and it is language-dependent — German 0.00 %, Korean 0.13 %, Japanese
+  0.41 %. Excluding that subset it lands near 1.7 % raw. Both ASRs agree the
+  audio genuinely degrades there, so it is the model, not the scorer.
+* **Normalization is where the weakest systems gain most, and the order does not
+  change.** The XTTS tokenizers have no Vietnamese number expansion, so raw text
+  punishes them hard (`challenging` 27.86 %) and the normalized column is the
+  fairest comparison available — it improves XTTS 2.3× and viXTTS 2.1×, against
+  1.8× for us. What remains is the acoustic model.
+* **`vietnamese` barely moves for anyone** (0.16 % → 0.21 % for ZeroTTS). It has
+  no digits or acronyms, so there is nothing to normalize — which is the control
+  showing the other subsets' gains are real and not a scoring artifact.
+* **On `cross_lingual` our voice similarity is the weak spot** (0.911 vs
+  ~0.935 for the others): ZeroTTS carries a foreign speaker's timbre into
+  Vietnamese slightly less faithfully, while winning that subset's WER by 12×.
+* **The WER definition matters more than the WER.** ZeroBench scores every clip
+  with **two ASRs** (`whisper-large-v3` + `PhoWhisper-large`, min taken — neither
+  can judge Vietnamese code-switch TTS alone) against **every acceptable
+  reading** of the target text, so a system is never charged for an ASR's
+  choice between "31/12/2025" and "ba mươi mốt tháng mười hai". Its test suite
+  pins that in both directions: format differences must score 0, real
+  mispronunciations must still cost.
+* **Our remaining errors are published, not hidden.** Every item scoring above
+  0.00 is audited in [docs/BENCHMARKS.md](https://github.com/zeroweight-ai/ZeroTTS/blob/main/docs/BENCHMARKS.md). The two recurring
+  ones: a leading zero read aloud (`18/04` → "tháng **không** tư"), and the
+  letters `W` and `H` coming out wrong when an acronym has to be spelled —
+  `WHO` should be spelled out letter by letter, and instead comes out as
+  something like "Hall".
+
+Reproduce, or score your own system:
+
+```bash
+pip install "zerotts[eval]"
+SYNTH_FROM=text_normalized OUT_DIR=./eval/norm ./evaluation/run_benchmark.sh
+./evaluation/run_benchmark.sh                                   # raw text
+```
+
+Not using ZeroTTS? The scorer stands alone — bring wavs from any system:
+
+```bash
+huggingface-cli download zeroweight-ai/ZeroBench-TTS --repo-type dataset --local-dir ZeroBench-TTS
+cd ZeroBench-TTS && pip install -r zerobench_eval/requirements.txt
+python -m zerobench_eval manifest --out manifest.jsonl    # what to synthesize
+python -m zerobench_eval score --wav_dir my_wavs/ --name MyModel
+```
+
 ## Voices, and voice cloning
 
 A voice is a small array of speaker latents, `(1, n_voice_queries, d_model)`,
@@ -198,6 +277,25 @@ conditioning — no reference transcript, no audio prompt.
 Because a voice is just an array, latents obtained that way drop into
 `voices/<name>/voice.npz` and work with no code change.
 
+## Repository layout
+
+```
+config.json                          runtime config
+tokenizer.json                       BPE tokenizer
+null_voice_emb.npy                   learned unconditional voice prefix
+onnx/text_encoder.onnx               text → encoder states (once per utterance)
+onnx/prefix_step.onnx                global transformer step (once per frame)
+onnx/local_frame_decode.onnx         frame decode + sampling (once per frame)
+onnx/codec/                          MOSS-Audio-Tokenizer-Nano decoder (Apache-2.0)
+voices/<name>/voice.npz              speaker latents
+```
+
+fp32, not quantized: ~900 MB total. Two ONNX Runtime calls per audio frame;
+frames are produced at 12.5 Hz and decoded to 48 kHz.
+
+The model architecture, training code, and the ONNX export script are not
+published, and the voice encoder is not included.
+
 ## Intended use and limitations
 
 Built for **Vietnamese**. It handles English words embedded in Vietnamese text
@@ -230,6 +328,7 @@ no external runtime dependency; the encoder is not included. See
 ## License
 
 ZeroTTS weights and code: **MIT**.
+Bundled MOSS codec decoder: **Apache-2.0**.
 
 The ZeroBench-TTS *dataset* is CC-BY-NC-4.0 because it redistributes reference
 audio from VIVOS, viVoice, phoaudiobook and Emilia. That license applies to the

silence_frame.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2628efa99ae02819b04ff7509ef43ddb3213a9fb0916e4e88b8d1a7c3a1810
+size 256

voices/arya/meta.json

@@ -1,7 +0,0 @@
-{
-  "name": "arya",
-  "language": "vi",
-  "description": "Giọng nữ, rõ ràng và trung tính",
-  "gender": "female",
-  "n_voice_queries": 10
-}

voices/baotrang/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "baotrang",
+  "display_name": "Bảo Trang",
+  "language": "vi",
+  "gender": "nữ",
+  "description": "nữ, trưởng thành, tin tức, rõ ràng, trung tính",
+  "tags": [
+    "nữ",
+    "trưởng thành",
+    "tin tức",
+    "rõ ràng",
+    "trung tính"
+  ],
+  "n_voice_queries": 10
+}

voices/{viVoice1 → baotrang}/preview.wav

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129face8e1bb175b43bfa6baabae3f3bbf61d5443199b09f01bb1770317a7992
-size 576044
+oid sha256:cfe47bfeabb0177c9f346bae41a42c655ee4531184938d536317470be6ab5cfd
+size 437804

voices/{viVoice1 → baotrang}/voice.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552f9fd7cc6cc5b2161a9b5248c8dd6745bf227b537bdbab4b5bfe14f2ea0df1
+oid sha256:db21fd1342da2d7d213f6b81d4795eee1be13f65410da99cfef4c92f3a80e29f
 size 30720

voices/{viVoice1 → baotrang}/voice.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30051535e078df5d6a7547c4b90a175c5a42aea4142c7122efc03a5e2c145f1d
+oid sha256:abbc5807cc4767e7c62cc59f7b7cd04b4b7e0dba176086447a0c114578cf695a
 size 31262

voices/giahuy/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "giahuy",
+  "display_name": "Gia Huy",
+  "language": "vi",
+  "gender": "nam",
+  "description": "nam, trẻ, kể chuyện, trầm ấm, tâm tình",
+  "tags": [
+    "nam",
+    "trẻ",
+    "kể chuyện",
+    "trầm ấm",
+    "tâm tình"
+  ],
+  "n_voice_queries": 10
+}

voices/{arya → giahuy}/preview.wav

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b762d566dc7cc734059114d955182f8f30341f6ccbc2c240eaa4ef98f31e2a
-size 459820
+oid sha256:16feeedc4bc930bbe5aad4e657d1df78e60abc11fcac179a42f75c0d268b25d1
+size 629804

voices/{arya → giahuy}/voice.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad725aed27afff9487c5a00c715027df481c93922028b698e1d61c59e134ff36
+oid sha256:1367686f7b5b154dc75b83d108487794c781812c6695a302f1b71afc821050ad
 size 30720

voices/{arya → giahuy}/voice.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee86069210c4b59e70d548c96830fe61d809c79ce321755f5f21e08b615473e
+oid sha256:3979a8369000eaaee1130801c1cacdadddc12e8d9a4a604be7430c4bcc6df32e
 size 31262

voices/hamy/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "hamy",
+  "display_name": "Hà My",
+  "language": "vi",
+  "gender": "nữ",
+  "description": "nữ, trẻ, hoạt hình, cao, biểu cảm",
+  "tags": [
+    "nữ",
+    "trẻ",
+    "hoạt hình",
+    "cao",
+    "biểu cảm"
+  ],
+  "n_voice_queries": 10
+}

voices/hamy/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aab12b5fa3d00b5e5dffe826b30fc7c7062c9e3da403d39831dab693d1f3f0d
+size 529964

voices/hamy/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a385bc5fc73bc11ebc7cbde39c447ed1b476cb9970c293bd4e26ff66fd11119d
+size 30720

voices/hamy/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b922963b868a0e403690194782b57f2a11aec55f59e0314566cb80bba71b332b
+size 31262

voices/huuduc/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "huuduc",
+  "display_name": "Hữu Đức",
+  "language": "vi",
+  "gender": "nam",
+  "description": "nam, lớn tuổi, kể chuyện, trầm, điềm đạm",
+  "tags": [
+    "nam",
+    "lớn tuổi",
+    "kể chuyện",
+    "trầm",
+    "điềm đạm"
+  ],
+  "n_voice_queries": 10
+}

voices/huuduc/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8241e4cefd7bc526e101f0d0db7a793b9e2159ffae9f2f2e3c1cc94edebec184
+size 491564

voices/huuduc/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82db4e47cea838d8678962b174ba5e141bf772f943e87f9115b303b1f8c3afe2
+size 30720

voices/huuduc/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a6370180263093eb9dd009661ba24b5309f0ba94ec18d8ff2323c80616a7eb
+size 31262

voices/index.json

@@ -1,9 +1,18 @@
 {
   "voices": [
     {
-      "name": "arya",
+      "name": "maichi",
+      "display_name": "Mai Chi",
       "language": "vi",
-      "description": "Giọng nữ, rõ ràng và trung tính",
+      "gender": "nữ",
+      "description": "nữ, trẻ, kể chuyện, nhẹ nhàng, thân thiện",
+      "tags": [
+        "nữ",
+        "trẻ",
+        "kể chuyện",
+        "nhẹ nhàng",
+        "thân thiện"
+      ],
       "n_voice_queries": 10,
       "shape": [
         1,
@@ -12,9 +21,158 @@
       ]
     },
     {
-      "name": "viVoice1",
+      "name": "baotrang",
+      "display_name": "Bảo Trang",
       "language": "vi",
-      "description": "Giọng đọc tự nhiên, tốc độ vừa phải",
+      "gender": "nữ",
+      "description": "nữ, trưởng thành, tin tức, rõ ràng, trung tính",
+      "tags": [
+        "nữ",
+        "trưởng thành",
+        "tin tức",
+        "rõ ràng",
+        "trung tính"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "kimoanh",
+      "display_name": "Kim Oanh",
+      "language": "vi",
+      "gender": "nữ",
+      "description": "nữ, trung niên, kể chuyện, ấm áp, truyền cảm",
+      "tags": [
+        "nữ",
+        "trung niên",
+        "kể chuyện",
+        "ấm áp",
+        "truyền cảm"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "giahuy",
+      "display_name": "Gia Huy",
+      "language": "vi",
+      "gender": "nam",
+      "description": "nam, trẻ, kể chuyện, trầm ấm, tâm tình",
+      "tags": [
+        "nam",
+        "trẻ",
+        "kể chuyện",
+        "trầm ấm",
+        "tâm tình"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "huuduc",
+      "display_name": "Hữu Đức",
+      "language": "vi",
+      "gender": "nam",
+      "description": "nam, lớn tuổi, kể chuyện, trầm, điềm đạm",
+      "tags": [
+        "nam",
+        "lớn tuổi",
+        "kể chuyện",
+        "trầm",
+        "điềm đạm"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "quangminh",
+      "display_name": "Quang Minh",
+      "language": "vi",
+      "gender": "nam",
+      "description": "nam, trẻ, tin tức, rõ ràng, dứt khoát",
+      "tags": [
+        "nam",
+        "trẻ",
+        "tin tức",
+        "rõ ràng",
+        "dứt khoát"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "tiendat",
+      "display_name": "Tiến Đạt",
+      "language": "vi",
+      "gender": "nam",
+      "description": "nam, trẻ, bình luận, sôi nổi, năng lượng cao",
+      "tags": [
+        "nam",
+        "trẻ",
+        "bình luận",
+        "sôi nổi",
+        "năng lượng cao"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "hamy",
+      "display_name": "Hà My",
+      "language": "vi",
+      "gender": "nữ",
+      "description": "nữ, trẻ, hoạt hình, cao, biểu cảm",
+      "tags": [
+        "nữ",
+        "trẻ",
+        "hoạt hình",
+        "cao",
+        "biểu cảm"
+      ],
+      "n_voice_queries": 10,
+      "shape": [
+        1,
+        10,
+        768
+      ]
+    },
+    {
+      "name": "thanhtruc",
+      "display_name": "Thanh Trúc",
+      "language": "vi",
+      "gender": "nữ",
+      "description": "nữ, trẻ, dịu dàng, thủ thỉ, nhẹ",
+      "tags": [
+        "nữ",
+        "trẻ",
+        "dịu dàng",
+        "thủ thỉ",
+        "nhẹ"
+      ],
       "n_voice_queries": 10,
       "shape": [
         1,

voices/kimoanh/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "kimoanh",
+  "display_name": "Kim Oanh",
+  "language": "vi",
+  "gender": "nữ",
+  "description": "nữ, trung niên, kể chuyện, ấm áp, truyền cảm",
+  "tags": [
+    "nữ",
+    "trung niên",
+    "kể chuyện",
+    "ấm áp",
+    "truyền cảm"
+  ],
+  "n_voice_queries": 10
+}

voices/kimoanh/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235bbe6aac7abbac191b2302ff52e51422076bf8117cd4142de1da7fe837a806
+size 721964

voices/kimoanh/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125a9dd8580ee96902868ea75ace8f572950a80a03b49e1cf4583332668844a0
+size 30720

voices/kimoanh/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aee413f25eae30123f930bd525d31a3b5a20c0803b4899305c2ff4a69466946
+size 31262

voices/maichi/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "maichi",
+  "display_name": "Mai Chi",
+  "language": "vi",
+  "gender": "nữ",
+  "description": "nữ, trẻ, kể chuyện, nhẹ nhàng, thân thiện",
+  "tags": [
+    "nữ",
+    "trẻ",
+    "kể chuyện",
+    "nhẹ nhàng",
+    "thân thiện"
+  ],
+  "n_voice_queries": 10
+}

voices/maichi/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b2c3fc41b652477139fc0b63bc35399e6d0d07b55470be4603e8024a64f4bf
+size 606764

voices/maichi/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ec8afe3a901cd781fff1a81b7624c3da38ded8d9fd2a2c88e11927b632cabb
+size 30720

voices/maichi/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bbc62df623764c5cf50b840bb27eb590b2385d7a72b9728494636ef677c6e6
+size 31262

voices/quangminh/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "quangminh",
+  "display_name": "Quang Minh",
+  "language": "vi",
+  "gender": "nam",
+  "description": "nam, trẻ, tin tức, rõ ràng, dứt khoát",
+  "tags": [
+    "nam",
+    "trẻ",
+    "tin tức",
+    "rõ ràng",
+    "dứt khoát"
+  ],
+  "n_voice_queries": 10
+}

voices/quangminh/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0257b6868a5ee37b2ef0f54d35d06c9d193c0358b2e66edc2ea7e1248608cb39
+size 391724

voices/quangminh/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1073679c7b82ce817f01ea5269307bbb9bb5c22717d218a419ca4185be390c
+size 30720

voices/quangminh/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2acb18f831ade23ed2d02e7b749fa745c95e9ee305795c5ddeb75f93d35fdb
+size 31262

voices/thanhtruc/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "thanhtruc",
+  "display_name": "Thanh Trúc",
+  "language": "vi",
+  "gender": "nữ",
+  "description": "nữ, trẻ, dịu dàng, thủ thỉ, nhẹ",
+  "tags": [
+    "nữ",
+    "trẻ",
+    "dịu dàng",
+    "thủ thỉ",
+    "nhẹ"
+  ],
+  "n_voice_queries": 10
+}

voices/thanhtruc/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e3120194132cd37ae79d6362aaa06cfc9bd971ec59e258be4f183bacbea5b6
+size 599084

voices/thanhtruc/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d443df8e986d5b08afe934c77764eaa76c326864407c2d6f96cbb09120acef5
+size 30720

voices/thanhtruc/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4103e4f3aaee2396bc2a1c986e2db1a2ae62b227ed0f1bcc2f1a9e4ef4d8ed1
+size 31262

voices/tiendat/meta.json

@@ -0,0 +1,15 @@
+{
+  "name": "tiendat",
+  "display_name": "Tiến Đạt",
+  "language": "vi",
+  "gender": "nam",
+  "description": "nam, trẻ, bình luận, sôi nổi, năng lượng cao",
+  "tags": [
+    "nam",
+    "trẻ",
+    "bình luận",
+    "sôi nổi",
+    "năng lượng cao"
+  ],
+  "n_voice_queries": 10
+}

voices/tiendat/preview.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833a33be52c083c56a11783e67d8cd953b794b8a4334e15e1c14bf11adaf966c
+size 483884

voices/tiendat/voice.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cc88e2144054b244e34f402e51bcf6342f6affde31c92ff1ce80d58c0ab5dd
+size 30720

voices/tiendat/voice.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a076fe7b938ad057652ffc4614678395edad90ab5cdc74546f3977636de15d0a
+size 31262

voices/viVoice1/meta.json

@@ -1,7 +0,0 @@
-{
-  "name": "viVoice1",
-  "language": "vi",
-  "description": "Giọng đọc tự nhiên, tốc độ vừa phải",
-  "gender": "",
-  "n_voice_queries": 10
-}