Upload Opal voice

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* 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
+asset/dingding.png filter=lfs diff=lfs merge=lfs -text
+sample/opal_0.wav filter=lfs diff=lfs merge=lfs -text
+sample/opal_1.wav filter=lfs diff=lfs merge=lfs -text
+sample/opal_2.wav filter=lfs diff=lfs merge=lfs -text

CosyVoice-BlankEN/config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

CosyVoice-BlankEN/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

CosyVoice-BlankEN/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

CosyVoice-BlankEN/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

README.md

@@ -0,0 +1,112 @@
+---
+license: apache-2.0
+base_model: FunAudioLLM/Fun-CosyVoice3-0.5B-2512
+tags:
+  - nanites
+  - tts
+  - text-to-speech
+  - cosyvoice3
+  - anonymized-voice
+  - appalachian
+  - smoky-mountains
+  - north-carolina
+  - tennessee
+  - "1939"
+  - historical-dialect
+language:
+  - en
+pipeline_tag: text-to-speech
+---
+
+# nanites-smoky-speech-otis / nanites-smoky-speech-opal
+
+Anonymized, gender-pooled Smoky Mountain English text-to-speech voices —
+the 1930s regional dialect of the Great Smoky Mountains (NC + TN) as
+recorded by Joseph Sargent Hall in 1939. Built on
+[Fun-CosyVoice3-0.5B-2512](https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512)
+(Apache-2.0, from FunAudioLLM), fine-tuned separately per gender. Second
+generation of the Smoky voices: new randomly-sampled speaker pools on
+the CosyVoice 3 engine (first generation: Earl + Ethel on CosyVoice2).
+
+## Personas
+
+The two pooled voices ship under Appalachian codenames so the identity
+is a *persona*, never a single Hall speaker:
+
+- **Otis** (male) — 15 speakers, 265 clips, 40.0 min. Best-8 epochs
+  `[10, 8, 9, 12, 13, 15, 11, 6]` by val loss. Samples: `sample/otis_0.wav`,
+  `sample/otis_1.wav`, `sample/otis_2.wav` (chatbot-written lines, same
+  three lines as Opal for comparison).
+- **Opal** (female) — 15 speakers, 160 clips, 24.8 min. Best-8 epochs
+  `[8, 14, 15, 13, 9, 12, 11, 16]` by val loss. Samples:
+  `sample/opal_0.wav`, `sample/opal_1.wav`, `sample/opal_2.wav`.
+
+In code/config the voices keep functional names
+`smoky-speech-male_v2` / `smoky-speech-female_v2` with speaker IDs
+`<|male_pool_v2|>` / `<|female_pool_v2|>`; "Otis" and "Opal" are the
+display/persona names. **Hugging Face repos are persona-named**:
+
+- `Nanite-Labs/nanites-smoky-speech-otis`
+- `Nanite-Labs/nanites-smoky-speech-opal`
+
+## Pools (random subsets, seed 20260925)
+
+Male v2 is fully disjoint from Earl (0 overlap). Female v2 reuses 10 of
+Ethel's speakers (only 6 unused female codes existed in the archive) plus
+5 fresh ones (`GladysHoyle, sr011am, sr038am, sr049bm, sr084am`):
+
+- male: `sr012bm, sr042am, sr042bm, sr048am, sr050bm, sr057bm, sr058am,
+  sr062bm, sr064bm, sr067bm, sr074am, sr076am, sr076bm, sr102bm, sr161bm`
+- female: `GladysHoyle, sr011am, sr011bm, sr033bm, sr038am, sr049am,
+  sr049bm, sr060am, sr066bm, sr068am, sr075am, sr075bm, sr084am, sr086am,
+  sr086bm`
+
+Pipeline per clip (same as v1): 16 kHz → 24 kHz resample,
+spectral-gate denoise, energy-VAD trim, SNR filter (≥ 8 dB).
+
+## Training
+
+- **Base:** `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` (llm.pt + flow.pt + hift.pt)
+- **Data:** pooled chunk sets → kaldi-style dirs
+  (`wav.scp/text/utt2spk` + per-utterance `instruct`:
+  `You are a helpful assistant.<|endofprompt|>`, required by the v3 LLM)
+  → campplus embeddings + v3 speech tokens → parquet →
+  `cosyvoice/bin/train.py` (`--model llm`, 1×GPU, bf16, constant-lr 1e-5,
+  `use_spk_embedding: True`). Single speaker ID per gender.
+- **8 GB recipe:** bitsandbytes AdamW8bit; whole model bf16 (no GradScaler);
+  gradient checkpointing (`COSYVOICE_GC=1`); DDP wrap skipped at world_size 1;
+  single-proc join guard. Patches live in `experts/smoky/train_sft.py`
+  (repo clone stays pristine).
+- **Outputs:** `llm_avg.pt` per gender (best-8 by val loss); voice dirs
+  assembled from the v3 base + averaged LLM + baked `spk2info.pt`.
+- **Inference note (v3):** synthesis text must carry the instruct prefix —
+  `You are a helpful assistant.<|endofprompt|>` is prepended automatically
+  by `experts/smoky/cosyvoice_infer.py` for v3 voice dirs. SFT mode only
+  (`inference_sft`, pooled embedding, no reference clip).
+
+```bash
+python experts/smoky/cosyvoice_infer.py \
+    --model_dir <voice-dir> \
+    --text "What was sharecropping like?" \
+    --sft_spk_id "<|male_pool_v2|>" \
+    --out out.wav
+```
+
+## Evaluation
+
+- **WER** (whisper `medium.en`, 3 novel chatbot-written dialect lines,
+  132 words): **Otis 6.1%**, **Opal 7.6%**. Target < 12%.
+  (Residual errors are dialect spellings: *crick→creek, dawnin→dawning*.)
+- **Anonymization:** pooled campplus embedding max cosine to the closest
+  pool-member mean: **0.924 (male) / 0.927 (female)** — a blended mean
+  identity matching no single speaker (v1: 0.888/0.909).
+- Sample lines were written by the collection's own chat model
+  (`nanites-smoky-1b-chat`) so text and speech share the regional register.
+
+## Provenance
+
+Audio: public-domain 1939 Hall field recordings (USC archive).
+Transcripts (Montgomery & Reed 2017, copyrighted) used locally only —
+never redistributed; training artifacts are derived phonetic tokens, not
+source text. Pooling is structural anonymization: one speaker ID per
+gender, no reference audio at inference.

campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

config.json

@@ -0,0 +1 @@
+{}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-to-speech"}

cosyvoice3.yaml

@@ -0,0 +1,223 @@
+# set random seed, so that you may reproduce your result.
+__set_seed1: !apply:random.seed [1986]
+__set_seed2: !apply:numpy.random.seed [1986]
+__set_seed3: !apply:torch.manual_seed [1986]
+__set_seed4: !apply:torch.cuda.manual_seed_all [1986]
+
+# fixed params
+sample_rate: 24000
+llm_input_size: 896
+llm_output_size: 896
+spk_embed_dim: 192
+qwen_pretrain_path: ''
+token_frame_rate: 25
+token_mel_ratio: 2
+
+# stream related params
+chunk_size: 25 # streaming inference chunk size, in token
+num_decoding_left_chunks: -1 # streaming inference flow decoder left chunk size, <0 means use all left chunks
+
+# model params
+# for all class/function included in this repo, we use !<name> or !<new> for intialization, so that user may find all corresponding class/function according to one single yaml.
+# for system/third_party class/function, we do not require this.
+llm: !new:cosyvoice.llm.llm.CosyVoice3LM
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    speech_token_size: 6561
+    length_normalized_loss: True
+    lsm_weight: 0
+    mix_ratio: [5, 15]
+    llm: !new:cosyvoice.llm.llm.Qwen2Encoder
+        pretrain_path: !ref <qwen_pretrain_path>
+    sampling: !name:cosyvoice.utils.common.ras_sampling
+        top_p: 0.8
+        top_k: 25
+        win_size: 10
+        tau_r: 0.1
+
+flow: !new:cosyvoice.flow.flow.CausalMaskedDiffWithDiT
+    input_size: 80
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: 'mel'
+    vocab_size: 6561
+    input_frame_rate: !ref <token_frame_rate>
+    only_mask_loss: True
+    token_mel_ratio: !ref <token_mel_ratio>
+    pre_lookahead_len: 3
+    pre_lookahead_layer: !new:cosyvoice.transformer.upsample_encoder.PreLookaheadLayer
+        in_channels: 80
+        channels: 1024
+        pre_lookahead_len: 3
+    decoder: !new:cosyvoice.flow.flow_matching.CausalConditionalCFM
+        in_channels: 240
+        n_spks: 1
+        spk_emb_dim: 80
+        cfm_params: !new:omegaconf.DictConfig
+            content:
+                sigma_min: 1e-06
+                solver: 'euler'
+                t_scheduler: 'cosine'
+                training_cfg_rate: 0.2
+                inference_cfg_rate: 0.7
+                reg_loss_type: 'l1'
+        estimator: !new:cosyvoice.flow.DiT.dit.DiT
+            dim: 1024
+            depth: 22
+            heads: 16
+            dim_head: 64
+            ff_mult: 2
+            mel_dim: 80
+            mu_dim: 80
+            spk_dim: 80
+            out_channels: 80
+            static_chunk_size: !ref <chunk_size> * <token_mel_ratio>
+            num_decoding_left_chunks: !ref <num_decoding_left_chunks>
+
+hift: !new:cosyvoice.hifigan.generator.CausalHiFTGenerator
+    in_channels: 80
+    base_channels: 512
+    nb_harmonics: 8
+    sampling_rate: !ref <sample_rate>
+    nsf_alpha: 0.1
+    nsf_sigma: 0.003
+    nsf_voiced_threshold: 10
+    upsample_rates: [8, 5, 3]
+    upsample_kernel_sizes: [16, 11, 7]
+    istft_params:
+        n_fft: 16
+        hop_len: 4
+    resblock_kernel_sizes: [3, 7, 11]
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    source_resblock_kernel_sizes: [7, 7, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    conv_pre_look_right: 4
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.CausalConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# gan related module
+mel_spec_transform1: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+hifigan: !new:cosyvoice.hifigan.hifigan.HiFiGan
+    generator: !ref <hift>
+    discriminator: !new:cosyvoice.hifigan.discriminator.MultipleDiscriminator
+        mpd: !new:matcha.hifigan.models.MultiPeriodDiscriminator
+        mrd: !new:cosyvoice.hifigan.discriminator.MultiResSpecDiscriminator
+    mel_spec_transform: [
+        !ref <mel_spec_transform1>
+    ]
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_qwen_tokenizer
+    token_path: !ref <qwen_pretrain_path>
+    skip_special_tokens: True
+    version: cosyvoice3
+allowed_special: 'all'
+tokenize: !name:cosyvoice.dataset.processor.tokenize
+    get_tokenizer: !ref <get_tokenizer>
+    allowed_special: !ref <allowed_special>
+filter: !name:cosyvoice.dataset.processor.filter
+    max_length: 40960
+    min_length: 100
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+truncate: !name:cosyvoice.dataset.processor.truncate
+    truncate_length: 24480 # must be a multiplier of hop_size
+feat_extractor: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+compute_f0: !name:cosyvoice.dataset.processor.compute_f0
+    sample_rate: !ref <sample_rate>
+    hop_size: 480
+parse_embedding: !name:cosyvoice.dataset.processor.parse_embedding
+    normalize: True
+shuffle: !name:cosyvoice.dataset.processor.shuffle
+    shuffle_size: 1000
+sort: !name:cosyvoice.dataset.processor.sort
+    sort_size: 500  # sort_size should be less than shuffle_size
+batch: !name:cosyvoice.dataset.processor.batch
+    batch_type: 'dynamic'
+    max_frames_in_batch: 2000
+padding: !name:cosyvoice.dataset.processor.padding
+    use_spk_embedding: False # change to True during sft
+
+
+# dataset processor pipeline
+data_pipeline: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <compute_fbank>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+data_pipeline_gan: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <truncate>,
+    !ref <compute_fbank>,
+    !ref <compute_f0>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+
+# llm flow train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 1e-5 # change to 1e-5 during sft
+    scheduler: constantlr # change to constantlr during sft
+    scheduler_conf:
+        warmup_steps: 2500
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 2
+    log_interval: 100
+    save_per_step: -1
+
+# gan train conf
+train_conf_gan:
+    optim: adam
+    optim_conf:
+        lr: 0.0002 # use small lr for gan training
+    scheduler: constantlr
+    optim_d: adam
+    optim_conf_d:
+        lr: 0.0002 # use small lr for gan training
+    scheduler_d: constantlr
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 1 # in gan training, accum_grad must be 1
+    log_interval: 100
+    save_per_step: -1

flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b51b9533a55937762b262bf2cf9c6220ce40760f76d6532cb16a6a6d84059a8
+size 1326216933

flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fab32a7825e5b0bc855ddd948f8db9370b0a786fbc249caa4595e95b608e4b
+size 1329116148

hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b279d7641eb97ae55b3b540cfba4f953c26492a2df758328a89a4d007ab87a65
+size 83202622

llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88959dc146ede72a505ec14cbb8fe94be5108e8ff4f55cd2badd0e170b25022
+size 1284661493

sample/opal_0.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93333c9dba1ae85c9ae48f7124a3e562b37ccef435b8e76389fbe538081c070
+size 791118

sample/opal_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f008a500fa5c8b7e44dfa770ab5c3bda4b6b3801958923ebec5c764de7d7684d
+size 604878

sample/opal_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1198aaad6c9f07404886294aabda7fca42e8371f76c631dff150b3fcd1c4fb
+size 862158

speech_tokenizer_v3.batch.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b156b8a7bbff436585e153f4637b9a368009005ac66efa108a6c8bfb34e5ee43
+size 969451579

speech_tokenizer_v3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23236a74175dbdda47afc66dbadd5bcb41303c467a57c261cb8539ad9db9208d
+size 969451503

spk2info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b127ccc5b7b003ba1fd2331fa7192b33de3d41f3046ef9f8c1fa4a5e192a5e5
+size 2416